Book Changelog
This Machine Learning Systems textbook is constantly evolving. This changelog is intended to record all updates and improvements, helping you stay informed about whatβs new and refined.
These changelog entries are automatically generated from our development process and should be mostly accurate. They track code changes, content updates, and improvements across the entire book. While the entries are comprehensive, they may occasionally contain minor inaccuracies or overly technical details.
2025 Updates
π August 01 at 04:54 PM
π Frontmatter
βββββ
About: The repository was restructured for better organization and maintainability, a cross-reference to Bloomβs figure was added, quizzes were added for self-assessment, and a bug in the -repair followed by repair sequence was fixedβββββ
SocratiQ: The repository was restructured for better organization and maintainability, an AI-powered figure caption improvement script was added, and PDF part summaries were implementedβββββ
Index: The index was restructured and updated with new section IDs and headers generated by a scriptβββββ
Foreword: The repository has been restructured to improve organization and maintainabilityβββββ
Changelog: The repository has been restructured to enhance organization and maintainabilityβββββ
Acknowledgements: The repository was restructured for better organization and maintainability, a bug in the repair functionality was fixed, and the script used for section generation was updated
π Chapters
βββββ
Chapter 1: Introduction: This update introduces auto-generated self-check quizzes throughout the introduction chapter and refactors the quiz generation process for improved efficiency. Section headers have also been updated for better navigationβββββ
Chapter 2: ML Systems: Quizzes with answers were added to the ML Systems chapter, section IDs were updated for consistent linking, and βConclusionβ sections were renamed to βSummaryββββββ
Chapter 3: DL Primer: New Tikz figures were added throughout the chapter, quizzes were integrated from JSON files, and βConclusionβ sections were renamed to βSummaryββββββ
Chapter 4: DNN Architectures: New TikZ figures were added to chapters 3-6, figure captions were updated for clarity, and descriptions were enhanced to clarify key conceptsβββββ
Chapter 5: AI Workflow: Quizzes were added to the chapter, quiz insertion logic was improved, and βConclusionβ sections were renamed to βSummaryββββββ
Chapter 6: Data Engineering: New Tikz figures were added to the chapter, descriptions and key concepts were enhanced for clarity, and quizzes were integratedβββββ
Chapter 8: AI Training: Added new TikZ figures to the chapter and integrated quizzes on efficient AI concepts. Renamed βConclusionβ sections to βSummaryββββββ
Chapter 9: Efficient AI: Quizzes were added to the Efficient AI chapter, section IDs were updated for consistent linking, and quiz answers were corrected and formattedβββββ
Chapter 10: Model Optimizations: Quizzes were added to the chapter and the quiz insertion logic was improved. Figure captions were updated for clarity and contextβββββ
Chapter 11: AI Acceleration: Quizzes were added to the chapter, quiz insertion logic was improved, and section headers and IDs were updated for consistencyβββββ
Chapter 13: ML Operations: The repository has been restructured for better organization and maintainability, quizzes have been added to the chapter, and the quiz insertion logic and answer extraction have been improvedβββββ
Chapter 14: On-Device Learning: Quizzes were added to the chapter, quiz insertion logic was improved, and section headers and IDs were updated for consistencyβββββ
Chapter 18: Robust AI: Improved quiz insertion logic, ensured quiz answers precede part blocks, and renamed βConclusionβ sections to βSummaryββββββ
Chapter 15: Security & Privacy: Quizzes were integrated into the chapter, figure captions were revised for improved clarity, and section IDs along with quiz JSON files were updatedβββββ
Chapter 16: Responsible AI: Quizzes were added to the chapter, quiz insertion logic was improved, and conclusion sections were renamed to summariesβββββ
Chapter 17: Sustainable AI: Standardized source citations throughout the chapter, integrated quizzes into the content, and improved the script for inserting and extracting quiz answersβββββ
Chapter 19: AI for Good: Quizzes were added to the chapter, quiz insertion logic was improved, and section IDs were updated for consistent linkingβββββ
Chapter 20: Conclusion: The repository was restructured for better organization and maintainability, section IDs were updated, βConclusionβ sections were renamed to βSummaryβ, and section anchors were added for self-check answersβββββ
PhD Survival Guide: The repository was restructured for better organization and maintainability, quiz answers are now correctly inserted before part blocks, anchor links were updated, and resources were moved to the backmatterβββββ
Design Principles: The repository has been restructured for better organization and maintainability, PDF part summaries have been implemented, and the bookβs part organization has been addedβββββ
Foundations: The repository has been restructured for better organization and maintainability, PDF part summaries have been implemented, and book part organization has been addedβββββ
Chapter 7: AI Frameworks: Added new TikZ figures to Chapters 7 and 8, removed resource sections from all chapters, and renamed βConclusionβ sections to βSummaryββββββ
Chapter 12: Benchmarking AI: Improved quiz insertion logic to ensure answers precede part blocks, updated figure and table captions for improved clarityβββββ
Chapter: Generative Ai: The repository has been restructured to improve organization and maintainabilityβββββ
Best Practices: The repository was restructured for better organization and PDF part summaries were implementedβββββ
Impact Outlook: The repository was restructured for better organization and PDF part summaries were implemented
π§βπ» Labs
βββββ
Lab: Nicla Vision: The lab repository has been restructured for better organization, figure captions have been corrected to adhere to style guidelines, a bug in the repair process was fixed, and the section generation script and section headers were updatedβββββ
Lab: Arduino Setup: The repository was restructured for better organization and maintainability, βConclusionβ sections were renamed to βSummaryβ, a bug in the repair command sequence was fixed, and section IDs were updated for consistent linkingβββββ
Lab: Arduino Image Classification: The labβs repository was restructured for better organization, βConclusionβ sections were renamed to βSummaryβ, a bug in the repair functionality was fixed, and section headers and IDs were updated for consistencyβββββ
Lab: Arduino Object Detection: The repository was restructured for better organization, βConclusionβ sections were renamed to βSummaryβ, a bug in the repair functionality was fixed, the section generation script was updated, and section IDs were revised for consistencyβββββ
Lab: Arduino Motion Classification: The repository was restructured for better organization, quiz answers are now inserted before part blocks as needed, and section IDs and headers were updatedβββββ
Lab: Xiao Esp32S3: The repository has been restructured for better organization, figure captions have been corrected to adhere to style guide, a bug in the -repair followed by repair function was fixed, and the section generation script and content consideration were updatedβββββ
Lab: Raspi: The repository has been restructured for better organization and maintainability, a bug in the -repair followed by repair sequence was fixed, and the section generation script and headers were updatedβββββ
Lab: Pi Image Classification: The repository was restructured for better organization and maintainability, βConclusionβ sections were renamed to βSummaryβ, a bug in the repair process was fixed, the script for section generation was updated, and section IDs were updated for consistent linkingβββββ
Lab: Pi Large Language Models: The repository was restructured for better organization, βConclusionβ sections were renamed to βSummaryβ, a bug in the repair functionality was fixed, and the section generation script and IDs were updatedβββββ
Lab: Pi Vision Language Models: The repository has been restructured for better organization and maintainability, quiz answers are now correctly inserted before part blocks, and section IDs and headers have been updatedβββββ
Lab: Labs: The repository has been restructured to improve organization and maintainabilityβββββ
Lab: Arduino Keyword Spotting: The repository has been restructured for better organization and maintainability, βConclusionβ sections have been renamed to βSummaryβ, a bug in the -repair followed by repair function was fixed, and section IDs were updated for consistent linkingβββββ
Lab: XIAO Setup: The repository has been restructured for better organization, βConclusionβ sections have been renamed to βSummaryβ, and a bug in the -repair followed by repair sequence was fixedβββββ
Lab: XIAO Image Classification: The repository has been restructured for better organization and maintainability, βConclusionβ sections have been renamed to βSummaryβ, a bug in the -repair followed by repair function was fixed, and section IDs were updated for consistent linkingβββββ
Lab: XIAO Object Detection: The repository was restructured for better organization and maintainability, βConclusionβ sections were renamed to βSummaryβ, and a bug in the -repair followed by repair sequence was fixedβββββ
Lab: XIAO Keyword Spotting: The repository was restructured for better organization and maintainability, βConclusionβ sections were renamed to βSummaryβ, and a bug in the -repair followed by repair sequence was fixedβββββ
Lab: XIAO Motion Classification: The repository has been restructured for better organization and maintainability, section headers have been updated, and quiz answers are now correctly placed before part blocksβββββ
Lab: Grove Vision Ai V2: The labβs repository was restructured, figure captions were corrected to adhere to style guidelines, a bug in the repair function was fixed, and the section generation script and section IDs were updatedβββββ
Lab: Setup And No Code Apps: The repository was restructured for better organization, βConclusionβ sections were renamed to βSummaryβ, and a bug in the -repair followed by repair sequence was fixedβββββ
Lab: Arduino Image Classification: The repository has been restructured for better organization, βConclusionβ sections have been renamed to βSummaryβ, and a bug in the -repair followed by repair process has been fixedβββββ
Lab: Arduino Object Detection: The repository has been restructured for improved organization and maintainabilityβββββ
Lab: Raspberry Pi Setup: The repository was restructured for better organization, source citations were standardized, and section IDs and headers were updatedβββββ
Lab: Pi Object Detection: The repository was restructured for better organization and maintainability, βConclusionβ sections were renamed to βSummaryβ, and the script used for section generation was updatedβββββ
Lab: Shared: The repository was restructured for better organization and the shared labs heading was updatedβββββ
Lab: Kws Feature Eng: The repository has been restructured for better organization and maintainability, βConclusionβ sections have been renamed to βSummaryβ, and a bug in the -repair followed by repair process has been fixedβββββ
Lab: Dsp Spectral Features Block: The repository was restructured for better organization and maintainability, section IDs were updated for consistent linking, and a bug in the -repair followed by repair sequence was fixedβββββ
Lab: Lab Setup: The repository has been restructured for better organization and maintainability, quiz answers are now inserted before part blocks when necessary, and βConclusionβ sections have been renamed to βSummaryββββββ
Lab: Labs Overview: The repository was restructured for better organization and maintainability, section IDs were updated to reflect content changes, and section headers were updated using a script
π Appendix
βββββ
PhD Survival Guide: The PhD Survival Guide now includes updated content, revised section IDs, and moved resources to the backmatter
π Jun 10 at 02:36 PM
π Frontmatter
βββββ
SocratiQ: Page links for SocratiQ were updated and documentation for the SocratiQ AI learning companion was addedβββββ
SocratiQ: The SocratiQ AI feature has been removed and minor grammatical and content errors have been correctedβββββ
About: SocratiQ page links were updated
π Chapters
βββββ
Chapter 4: DNN Architectures: Resource sections were added to the chapter content, text processing in QMD files was improved, and explanations of deep learning architectures were refinedβββββ
Chapter 5: AI Workflow: This chapter now includes resource sections, benefits from improved QMD text processing, and features new figures to enhance understandingβββββ
Chapter 6: Data Engineering: This update includes a new data pipeline overview diagram, replaces Mermaid diagrams with TikZ, and removes a broken web scraping Colab linkβββββ
Chapter 9: Efficient AI: Resource sections were added to the chapter content, the compute-optimal scaling frontier was clarified, and the language in the scaling laws section was refinedβββββ
Chapter 10: Model Optimizations: This update clarifies pruning strategies, incorporates resource sections into core content, and refines the documentation on model optimization techniquesβββββ
Chapter 13: ML Operations: Resource sections were added to the chapter, MLOps content was updated for clarity and accuracy, and the operations diagram and text were revisedβββββ
Chapter 14: On-Device Learning: Resource sections were added to the chapter content, the equations for adapter-based adaptation were clarified, and explanations and concepts were refined throughoutβββββ
Chapter 18: Robust AI: Resource sections were added to the chapter content, text processing in QMD files was improved, and a figure environment for error masking was implementedβββββ
Chapter 15: Security & Privacy: Added a threat mitigation flow diagram and an ML lifecycle threat diagram, and expanded the discussion on ML model threatsβββββ
Chapter 16: Responsible AI: Expanded the Responsible AI chapter with new sections on governance structures, safety and robustness considerations, privacy architectures, fairness constraints, system explainability, deployment contexts, and detailed discussions on safety, privacy, and fairness. IMPACTβββββ
Chapter 19: AI for Good: Resource sections were added to the chapter, text processing in QMD files was improved, and the AI for Good content was refined for clarityβββββ
Chapter 1: Introduction: The introduction now includes additional footnotes and has been revised for improved grammar and clarityβββββ
Chapter 2: ML Systems: Resource sections were added to the chapter content, the TinyML example callout was removed, and minor grammatical and content errors were correctedβββββ
Chapter 3: DL Primer: Resource sections were added to the chapter content, minor grammatical and content errors were corrected, and the difference between training and inference was clarifiedβββββ
Chapter 7: AI Frameworks: Resource sections were added to the chapter content, text processing in QMD files was improved, and figure references along with a parallelization typo were fixedβββββ
Chapter 8: AI Training: Resource sections were added to the core content, text processing in QMD files was improved, and the explanation of activation checkpointing was clarifiedβββββ
Chapter 11: AI Acceleration: Resource sections were added to the chapter, placement and allocation definitions were clarified, and code block language was corrected for clarityβββββ
Chapter 12: Benchmarking AI: Resource sections were added to the chapter content, text processing in QMD files was improved, and a typo was correctedβββββ
Chapter 17: Sustainable AI: Resource sections were added to the chapter content, minor grammatical and content errors were corrected, and text processing in QMD files was improved
π§βπ» Labs
βββββ
Lab: Grove Vision Ai V2: A new lab has been added focusing on Grove Vision AI v2 and its documentation has been improvedβββββ
Lab: Setup And No Code Apps: A new lab on Grove Vision AI v2 was added, and the existing documentation was improved with clarifications and typo correctionsβββββ
Lab: Arduino Image Classification: A new lab demonstrating image classification using the Grove Vision AI V2 module has been added to the textbookβββββ
Lab: Arduino Object Detection: A new lab demonstrating object detection with Grove Vision AI v2 and Arduino has been addedβββββ
Lab: Lab Setup: The lab setup instructions were updated with clearer installation steps and links to required softwareβββββ
Lab: Labs Overview: Lab file templates were updated and instructions for using Jupyter notebooks were addedβββββ
Lab: XIAO Image Classification: A typo was corrected in the image classification lab
π May 14 at 07:26 PM
π Chapters
βββββ
Chapter 14: On-Device Learning: The on-device learning content has been refactored and clarified for improved understanding
π May 14 at 04:04 PM
π Chapters
βββββ
Chapter 14: On-Device Learning: The on-device learning content has been refactored and clarified for better understanding
π May 04 at 08:18 PM
π Chapters
βββββ
Chapter 5: AI Workflow: The chapter now includes clarified data preprocessing steps, a new section on model evaluation metrics, and updated examples for real-world applicationsβββββ
Chapter 6: Data Engineering: Updated explanations of data pipelines, added examples of real-world data engineering tools, and improved clarity on data wrangling techniquesβββββ
Chapter 10: Model Optimizations: Updated explanations of gradient descent variants, added examples of momentum optimization techniques, and improved clarity on adaptive learning rate methodsβββββ
Chapter 11: AI Acceleration: The discussion on hardware acceleration has been refined, with enhancements to the explanation of hardware specialization and clarification regarding AI compute primitivesβββββ
Chapter 12: Benchmarking AI: The chapter now uses βMotivationβ instead of βPurposeβ, provides clearer explanations of benchmarking metrics and power measurements, and includes a script to identify missing referencesβββββ
Chapter 13: ML Operations: The chapter now features consolidated TikZ figure styling, expanded MLOps core concepts and case studies, and corrected acronym inconsistenciesβββββ
Chapter 14: On-Device Learning: Added a Federated Learning section, explored on-device learning strategies for limited data, and expanded the discussion on security considerations in on-device learningβββββ
Chapter 1: Introduction: The introduction chapter has been updated with improved content and clarityβββββ
Chapter 2: ML Systems: The chapter now has improved footnote formatting, a removed redundant definition, corrected grammar in the GDPR/HIPAA footnote, and a script was run to identify any missing referencesβββββ
Chapter 3: DL Primer: The dimension order for W^L was swapped and a script was added to identify any missing referencesβββββ
Chapter 4: DNN Architectures: The chapter was updated to ensure all references are present and correctβββββ
Chapter 7: AI Frameworks: Content from Chapter 6 was integrated and various fixes were implementedβββββ
Chapter 8: AI Training: Minor issues were fixed and label checking was improvedβββββ
Chapter 18: Robust AI: Minor issues were fixed, label checking was improved, and a script was added to locate missing referencesβββββ
Chapter 15: Security & Privacy: Minor issues were fixed and label checking was improvedβββββ
Chapter 17: Sustainable AI: TikZ figure styling was consolidated and a script was created to locate missing referencesβββββ
Chapter 19: AI for Good: The PlantVillage Nuru footnote accuracy was updated and a script was used to find any missing referencesβββββ
Chapter 9: Efficient AI: Bravo fixed several errors in the text of Chapter 9
π§βπ» Labs
βββββ
Lab: Arduino Keyword Spotting: Fixed keyword recognition accuracy, optimized the code for efficiency, and added a troubleshooting section for common issuesβββββ
Lab: Raspi: Updated Raspberry Pi setup instructions, added a TensorFlow Lite on Raspi section, and improved image classification code examplesβββββ
Lab: Pi Object Detection: The lab now includes updated code and instructions for utilizing a Raspberry Pi camera module for object detectionβββββ
Lab: Arduino Setup: The Nicla setup instructions were updated for clarity and accuracyβββββ
Lab: Arduino Image Classification: The labβs formatting, wording, instructions, documentation, text content, and images have been revised for clarity and accuracyβββββ
Lab: Arduino Object Detection: Formatting was updated and object detection instructions were clarifiedβββββ
Lab: Arduino Motion Classification: The code has been fixed to compile correctly and updated to utilize a more efficient motion detection algorithmβββββ
Lab: Xiao Esp32S3: Updated lab instructions and added code examples for sensor integration on the Xiao ESP32S3 boardβββββ
Lab: XIAO Setup: The LABS part 2_seeed_xiao_esp32s3 has been updatedβββββ
Lab: XIAO Image Classification: Fixes were made to the LABS part 2_seeed_xiao_esp32s3βββββ
Lab: XIAO Object Detection: The XIAO Object Detection lab has been updated with changes to LABS part 2_seeed_xiao_esp32s3βββββ
Lab: XIAO Keyword Spotting: The XIAO Keyword Spotting lab now includes updated code and explanations of ESP32S3 features utilizedβββββ
Lab: XIAO Motion Classification: The XIAO ESP32S3 motion classification lab code was updated with added explanations and commentsβββββ
Lab: Raspberry Pi Setup: The Raspberry Pi setup instructions have been updated to reflect the latest software versions and provide clearer guidanceβββββ
Lab: Pi Image Classification: The Raspberry Pi image classification lab now features updated code and clearer instructions for executionβββββ
Lab: Pi Large Language Models: The Raspberry Pi instructions were updated and additional links to relevant resources were includedβββββ
Lab: Pi Vision Language Models: The VLM lab guide has been refactored for improved clarity and the LABS part_raspi has been updatedβββββ
Lab: Kws Feature Eng: The shared labs section has been updatedβββββ
Lab: Dsp Spectral Features Block: The LABS part_shared has been updated
π Mar 26 at 03:56 AM
π Chapters
βββββ
Chapter 13: ML Operations: An exercise reference was removed and another was fixedβββββ
Chapter 18: Robust AI: Corrected formatting issues by fixing missing package and line commands and adding helvetica font
π Mar 25 at 11:51 PM
π Frontmatter
βββββ
Foreword: The foreword has been updated based on feedback from vale testingβββββ
About: The text has been updated based on feedback from vale testingβββββ
Acknowledgements: The contributors list has been updatedβββββ
SocratiQ: Trailing whitespace was removed and all broken links were fixed
π Chapters
βββββ
Chapter 9: Efficient AI: A new Scaling Laws section was added to the chapter, section headers were updated, and epoch AI figures were insertedβββββ
Chapter 13: ML Operations: The MLOps key components section was updated, the focus shifted from embedded Ops to Operational design principles, references were added, and case studies were updatedβββββ
Chapter 18: Robust AI: This chapter now includes a new introduction paragraph, updated information on poisoning attacks and permanent faults within the attacks section, and improvements to the real-world applications sectionβββββ
Chapter 17: Sustainable AI: This update includes a plot and discussion about Jevonβs paradox, along with fixes for broken linksβββββ
Chapter 1: Introduction: The introduction chapter now has consistent footnote naming, removed unnecessary code and packages, and had its Markdown styling cleaned upβββββ
Chapter 2: ML Systems: Fixed hyphenation issues, corrected a typo that caused PDF build errors, standardized Markdown styles, incorporated footnotes and ensured consistent footnote naming conventions, and addressed missing referencesβββββ
Chapter 3: DL Primer: Markdown styles were cleaned up, a new definition was added, footnotes were updated for consistency, and footnote naming conventions were standardizedβββββ
Chapter 4: DNN Architectures: Hyphenation is now handled globally via headerfile, Markdown styles were cleaned up, and all broken links have been fixedβββββ
Chapter 5: AI Workflow: A definition was added and references were updatedβββββ
Chapter 6: Data Engineering: The chapter now uses consistent hyphenation, improved Markdown formatting, updated section headers, and includes Mermaid diagramsβββββ
Chapter 7: AI Frameworks: A figure illustrating ONNX was added and footnote naming conventions were standardized for consistency. Callout formatting was also correctedβββββ
Chapter 8: AI Training: Updated footnote naming to be consistent and fixed missing figure references while cleaning up Markdown stylesβββββ
Chapter 10: Model Optimizations: This update includes various fixes for spelling, Markdown formatting, footnotes, PDF generation, and TikZ codeβββββ
Chapter 11: AI Acceleration: The chapter received spelling corrections, consistent Markdown styling for formatting elements like colons and tables, and updated references for footnotes and figuresβββββ
Chapter 12: Benchmarking AI: This chapter now has corrected links, updated section headers, and a resolved missing figure referenceβββββ
Chapter 14: On-Device Learning: The chapterβs Markdown styling was cleaned up and all broken links were fixedβββββ
Chapter 15: Security & Privacy: The chapter now has consistent Markdown styling and all broken links have been fixedβββββ
Chapter 16: Responsible AI: The chapterβs markdown formatting was cleaned up and all broken links were fixedβββββ
Chapter 19: AI for Good: The chapter now has consistent footnote naming, fixed broken links, and improved Markdown stylingβββββ
Chapter 20: Conclusion: Dangling sections were removed and the chapter underwent a first pass of revisionsβββββ
Chapter: Old Sus Ai: The chapter content has been updated and improvedβββββ
Chapter: Generative Ai: The Generative AI chapter received its initial draft content
π§βπ» Labs
βββββ
Lab: Arduino Setup: Markdown styles were cleaned up and all broken links in the Arduino setup instructions were fixedβββββ
Lab: Arduino Motion Classification: The labβs Markdown formatting was cleaned up and all broken links were fixedβββββ
Lab: Pi Vision Language Models: The labβs Markdown formatting has been cleaned up and all broken links have been fixedβββββ
Lab: Arduino Image Classification: Markdown styles were cleaned up in the image classification labβββββ
Lab: Arduino Keyword Spotting: The Markdown styles in the file were cleaned upβββββ
Lab: XIAO Image Classification: Spelling mistakes have been fixed in the XIAO Image Classification labβββββ
Lab: XIAO Keyword Spotting: Spelling errors were corrected and markdown styles were cleaned upβββββ
Lab: XIAO Motion Classification: Markdown styles were updated for consistency throughout the labβββββ
Lab: Raspberry Pi Setup: Spelling mistakes have been fixed throughout the lab setup instructionsβββββ
Lab: Pi Object Detection: All broken links were fixed and Markdown styles were cleaned upβββββ
Lab: Pi Large Language Models: Markdown styles were cleaned up in the lab filesβββββ
Lab: Kws Feature Eng: Markdown styles were cleaned up throughout the labβββββ
Lab: Dsp Spectral Features Block: Spelling errors were corrected and colon formatting was updated for consistency
π Appendix
βββββ
PhD Survival Guide: The PhD Survival Guide now has corrected spelling and all broken links have been repaired
π Mar 03 at 04:45 PM
π Frontmatter
βββββ
SocratiQ: Callout titles are now formatted correctly and linting issues with QMD files have been resolvedβββββ
About: Header spacing was adjusted for consistencyβββββ
Acknowledgements: The contributors list has been updated and reflected in the readme and acknowledgements file
π Chapters
βββββ
Chapter 10: Model Optimizations: This chapter now includes sections on structured optimization, post-training quantization (PTQ) and quantization aware training (QAT), sparsity visualization techniques, knowledge distillation (KD) figures, and learning transfer hardening (LTH) along with iterative pruning and calibrationβββββ
Chapter 11: AI Acceleration: This update includes a new discussion on hybrid mapping strategies and a visualization comparing models to memory bandwidth. The chapter overview and definition have also been updatedβββββ
Chapter 1: Introduction: Fixed callout title formatting and resolved issues with QMD file lintingβββββ
Chapter 2: ML Systems: Markdown and linting issues in the chapter were addressedβββββ
Chapter 3: DL Primer: Callout titles were formatted for consistency and the chapter content was updated with linting fixesβββββ
Chapter 4: DNN Architectures: Callout title formatting and QMD file linting were correctedβββββ
Chapter 5: AI Workflow: Redundant definitions were removed, text errors were corrected, and QMD file linting was improvedβββββ
Chapter 7: AI Frameworks: Images illustrating data and model parallelism were added, redundant definitions were removed, and log file handling was updatedβββββ
Chapter 8: AI Training: The chapter now includes descriptions of single and multi GPU systems, removed redundant definitions like β(GPUs)β, and fixed markdown formatting issuesβββββ
Chapter 9: Efficient AI: Redundant definitions were removed from the chapter, and spacing and linting issues were fixedβββββ
Chapter 12: Benchmarking AI: The chapter now uses TikZ code for images, includes a new image illustrating datacentric AI, and features corrected references and citationsβββββ
Chapter 13: ML Operations: Definitions were removed to avoid redundancy, callout titles are now formatted correctly, and QMD file linting was correctedβββββ
Chapter 18: Robust AI: Definitions were removed to avoid redundancy and formatting issues in the Markdown content were fixedβββββ
Chapter 15: Security & Privacy: Definitions were removed to avoid redundancy and formatting issues in Markdown were fixed for improved readabilityβββββ
Chapter 17: Sustainable AI: Redundant definitions were removed, callout titles were formatted correctly, and QMD file linting was fixedβββββ
Chapter 19: AI for Good: Redundant definitions were removed, callout title formatting was fixed, and QMD file linting issues were resolvedβββββ
Chapter 6: Data Engineering: Formatting and linting improvements were made to the Data Engineering chapterβββββ
Chapter 14: On-Device Learning: Typos were corrected, redundant definitions like those for GPUs were removed, and callout titles were formatted correctlyβββββ
Chapter 16: Responsible AI: Callout title formatting and QMD file linting were corrected
π§βπ» Labs
βββββ
Lab: Arduino Keyword Spotting: The Arduino keyword spotting lab now includes updated code examples, clearer explanations of key concepts, and improved lab instructionsβββββ
Lab: Nicla Vision: The Arduino/Nicla Vision LABS section has been updatedβββββ
Lab: Arduino Setup: The Arduino setup section for the nicla_vision LABS has been updatedβββββ
Lab: Arduino Image Classification: The Arduino image classification lab has been updated with changes to the labs sectionβββββ
Lab: Arduino Object Detection: The Arduino Object Detection LABS section has been updatedβββββ
Lab: Arduino Motion Classification: The Arduino/Nicla Vision LABS section was updated and header spacing was improved for better readabilityβββββ
Lab: Pi Vision Language Models: The lab now has corrected markdown formatting, improved linting for QMD files, and consistent header spacingβββββ
Lab: Kws Feature Eng: The lab notebook now has corrected Markdown formatting and resolved linting errorsβββββ
Lab: Labs Overview: Linting errors in QMD files have been corrected
π Feb 08 at 12:29 AM
π Frontmatter
βββββ
Acknowledgements: The contributor list has been updated to include all contributors and correct any omissionsβββββ
SocratiQ: Included a link to the Socratiq research paper
π Feb 07 at 11:50 PM
π Frontmatter
βββββ
About: The precheck script now only runs on qmd and bib filesβββββ
Changelog: The changelog is now automatically generated and updated within the frontmatterβββββ
SocratiQ: The SocratiQ precheck script now only runs on qmd and bib filesβββββ
Index: The precheck now only runs on .qmd and .bib filesβββββ
Acknowledgements: The acknowledgements section now includes a list of contributors to the textbook
π Chapters
βββββ
Chapter 12: Benchmarking AI: This update incorporates MLPerf power trend data, integrates a FastML science graph, and enhances the benchmarking challenges section with new visualizationsβββββ
Chapter 1: Introduction: The code now directly uses _quarto.yml and the precheck script only runs on qmd and bib filesβββββ
Chapter 2: ML Systems: The ML Systems chapter content was updated and the precheck script now only runs on .qmd and .bib filesβββββ
Chapter 3: DL Primer: The precheck script has been updated to run only on .qmd and .bib filesβββββ
Chapter 4: DNN Architectures: The precheck script now only runs on qmd and bib filesβββββ
Chapter 5: AI Workflow: The precheck functionality is now limited to running on .qmd and .bib filesβββββ
Chapter 6: Data Engineering: The precheck script now only runs on qmd and bib filesβββββ
Chapter 7: AI Frameworks: The code now directly utilizes _quarto.yml and the precheck script is limited to running on qmd and bib filesβββββ
Chapter 8: AI Training: Fixed figure formatting, updated a diagram, and removed an unused library from the codeβββββ
Chapter 9: Efficient AI: The code now uses only _quarto.yml, a bib reference was corrected, and R code was added for debugging and visualization purposesβββββ
Chapter 10: Model Optimizations: The precheck function now only runs on qmd and bib filesβββββ
Chapter 11: AI Acceleration: The precheck script now only runs on qmd and bib filesβββββ
Chapter 13: ML Operations: The precheck script now only runs on qmd and bib filesβββββ
Chapter 14: On-Device Learning: The precheck script now only runs on qmd and bib filesβββββ
Chapter 18: Robust AI: The precheck script now only runs on qmd and bib filesβββββ
Chapter 15: Security & Privacy: The precheck script is updated to run only on qmd and bib filesβββββ
Chapter 16: Responsible AI: The precheck script is updated to run only on .qmd and .bib filesβββββ
Chapter 17: Sustainable AI: The precheck now only runs on .qmd and .bib filesβββββ
Chapter 19: AI for Good: The code now directly uses _quarto.yml instead of an in-use library, PNG images are cached locally instead of being fetched from a broken remote URL, and the precheck function now only runs on qmd and bib filesβββββ
Chapter 20: Conclusion: The precheck now only runs on .qmd and .bib files
π§βπ» Labs
βββββ
Lab: Arduino Setup: The precheck script now only runs on .qmd and .bib filesβββββ
Lab: Arduino Image Classification: The precheck script now only runs on .qmd and .bib filesβββββ
Lab: Arduino Keyword Spotting: The precheck script now only runs on qmd and bib filesβββββ
Lab: Arduino Motion Classification: The precheck now only runs on .qmd and .bib filesβββββ
Lab: XIAO Setup: The precheck script now only runs on qmd and bib filesβββββ
Lab: XIAO Image Classification: The precheck script now only runs on .qmd and .bib filesβββββ
Lab: XIAO Object Detection: The precheck script now only runs on qmd and bib filesβββββ
Lab: XIAO Keyword Spotting: The precheck script now only runs on .qmd and .bib filesβββββ
Lab: XIAO Motion Classification: The precheck script now only runs on .qmd and .bib filesβββββ
Lab: Raspi: The precheck script now only runs on qmd and bib filesβββββ
Lab: Raspberry Pi Setup: The precheck script now only runs on qmd and bib filesβββββ
Lab: Pi Image Classification: The precheck script now only runs on qmd and bib filesβββββ
Lab: Pi Object Detection: The precheck script now only runs on qmd and bib filesβββββ
Lab: Pi Large Language Models: The precheck script now only runs on qmd and bib filesβββββ
Lab: Pi Vision Language Models: The precheck script now only runs on qmd and bib filesβββββ
Lab: Shared: The precheck script now only runs on qmd and bib filesβββββ
Lab: Kws Feature Eng: The precheck script now only runs on qmd and bib filesβββββ
Lab: Dsp Spectral Features Block: The precheck script now only runs on qmd and bib filesβββββ
Lab: Lab Setup: The precheck script now only runs on qmd and bib filesβββββ
Lab: Labs Overview: The precheck script now only runs on qmd and bib files
π Appendix
βββββ
PhD Survival Guide: The precheck script now only runs on qmd and bib files
π Feb 02 at 11:14 PM
π Frontmatter
βββββ
Acknowledgements: The acknowledgements section now includes a list of contributors to the textbook
π Chapters
βββββ
Chapter 12: Benchmarking AI: The chapter now has improved learning objectives, a corrected table and references, an updated case study, and reorganized contentβββββ
Chapter 1: Introduction: All ###* callout titles have been updated to use a title block formatβββββ
Chapter 2: ML Systems: All ###* callout titles have been updated to use a title block formatβββββ
Chapter 3: DL Primer: All callout ###* titles have been updated to use a title block formatβββββ
Chapter 5: AI Workflow: All callout ###* titles have been updated to a title block formatβββββ
Chapter 6: Data Engineering: All callout ###* titles have been updated to a title block formatβββββ
Chapter 7: AI Frameworks: The way the TikZ package is used in the chapter has been restructured by moving its declaration outside of begin{..} and into a header fileβββββ
Chapter 8: AI Training: Figure 8.8 was updated and several new diagrams were added to the chapter along with corrections to Python codeβββββ
Chapter 9: Efficient AI: Callout titles were updated to a title block format, the bibliography was updated, and an incorrect entry was removedβββββ
Chapter 11: AI Acceleration: All ###* callout titles have been updated to use a title block formatβββββ
Chapter 13: ML Operations: All ###* callout titles have been updated to a title block formatβββββ
Chapter 14: On-Device Learning: All ###* callout titles have been updated to use a title block formatβββββ
Chapter 18: Robust AI: All ###* callout titles have been updated to a title block formatβββββ
Chapter 15: Security & Privacy: All ###* callout titles have been updated to use a title block formatβββββ
Chapter 16: Responsible AI: All ###* callout titles have been updated to use a title block formatβββββ
Chapter 17: Sustainable AI: All ###* callout titles have been updated to use a title block formatβββββ
Chapter 19: AI for Good: All ###* callout titles have been updated to use a title block formatβββββ
Chapter 4: DNN Architectures: Errata were fixed and all callout ###* titles were updated to a title block formatβββββ
Chapter 10: Model Optimizations: All callout ###* titles have been updated to a title block format
π Jan 28 at 11:09 AM
π Frontmatter
βββββ
Acknowledgements: The acknowledgements section now includes a list of contributors
π Jan 28 at 07:14 AM
π Frontmatter
βββββ
Acknowledgements: The acknowledgements section now includes logos and an updated list of contributors
π Chapters
βββββ
Chapter 5: AI Workflow: A new section on data preprocessing techniques was added, example code for feature scaling was updated, and the explanation of hyperparameter tuning was clarifiedβββββ
Chapter 6: Data Engineering: The data section now includes more citations, and edits were made to the later data engineering sections. Keyword selection is also being worked onβββββ
Chapter 8: AI Training: Figures were added illustrating chips, references in the chapter were updated to align with the hardware section, and the training chapter was significantly improved with numerous updatesβββββ
Chapter 19: AI for Good: The chapter includes new videos, images, updated learning objectives, and added spotlight use casesβββββ
Chapter 2: ML Systems: Radar plots were added to Chapter 2βββββ
Chapter 7: AI Frameworks: Added figures illustrating different types of chips and included small bibliographic referencesβββββ
Chapter 9: Efficient AI: Learning objectives were added, references were updated, and figures were incorporated into the chapterβββββ
Chapter 11: AI Acceleration: References were removed from the chapterβββββ
Chapter 1: Introduction: A redundant case study was removedβββββ
Chapter 4: DNN Architectures: The chapterβs wording has been refined and corrected based on recommendationsβββββ
Chapter 10: Model Optimizations: Dead references were removed from the chapter
π§βπ» Labs
βββββ
Lab: Pi Image Classification: The lab now includes updated code for image classification, expanded explanations of the model training process, and clearer instructionsβββββ
Lab: Pi Object Detection: The object detection lab now features updated code, clearer explanations for model training, and improved instructions
π Appendix
βββββ
PhD Survival Guide: Several resources were added and one existing link was updated
π Jan 17 at 07:05 AM
π Frontmatter
βββββ
About: The book now includes updated information on recent machine learning advancements, a new section on ethical considerations in AI, and improved clarity throughout the textβββββ
SocratiQ: Updated SocratiQ platform details, added use case examples, and clarified key feature explanationsβββββ
Acknowledgements: The acknowledgements section now includes a list of contributors
π Chapters
βββββ
Chapter 3: DL Primer: The chapter now provides clearer distinctions between supervised and unsupervised learning, includes examples of popular DL architectures, and offers updated explanations of activation functionsβββββ
Chapter 7: AI Frameworks: This chapter now includes an overview of AI frameworks, updated learning objectives, and a section on the history of these frameworksβββββ
Chapter 1: Introduction: Incorporated Bravoβs feedback into the introductionβββββ
Chapter 4: DNN Architectures: Clarified the parameter storage bound for Recurrent Neural Networks and removed an unused footnoteβββββ
Chapter 2: ML Systems: PDF rendering issues were fixedβββββ
Chapter 6: Data Engineering: Incorporated feedback provided by Bravoβββββ
Chapter 12: Benchmarking AI: Fixed a reference issue in the chapter
π§βπ» Labs
βββββ
Lab: Pi Vision Language Models: Updated code snippets, added explanations for model training steps, and improved the clarity of VLM conceptsβββββ
Lab: Pi Large Language Models: Copyediting errors were corrected
π Jan 12 at 03:40 PM
π Frontmatter
βββββ
Acknowledgements: The contributor list has been updated and PDF rendering has been improved
π Chapters
βββββ
Chapter 1: Introduction: Fixed a rendering issue with triple quotes in the PDF version and made minor adjustments to section headersβββββ
Chapter 2: ML Systems: A definition for hybrid ML was added and PDF rendering was improvedβββββ
Chapter 5: AI Workflow: Zishen implemented fixes for improved PDF renderingβββββ
Chapter 6: Data Engineering: Updated figure sizes and the data labeling section with fixes from Zishen and other contributors
π Jan 11 at 04:51 PM
π Frontmatter
βββββ
Acknowledgements: The contributor list has been updated to include all contributors and correct any omissions
π Chapters
βββββ
Chapter 2: ML Systems: A decision playbook framework was added and definitions were updated and provided for each sectionβββββ
Chapter 5: AI Workflow: A grammar fix request was removedβββββ
Chapter 6: Data Engineering: Corrected errors present in Bravoβs contributions to the chapter
π Jan 11 at 02:09 AM
π Frontmatter
βββββ
Acknowledgements: The contributor list has been updated to include all contributors and correct any omissionsβββββ
About: The About section has been revised for improved clarity and concisenessβββββ
SocratiQ: The SocratiQ content was edited
π Chapters
βββββ
Chapter 1: Introduction: Footnotes have been added throughout the introduction section for additional context and referencesβββββ
Chapter 6: Data Engineering: The chapter includes added references, updated information on synthetic data and crowdsourcing, revised web scraping content, a refined problem definition, and minor updates to the overview
π Jan 09 at 11:49 AM
π Frontmatter
βββββ
Acknowledgements: The contributor list has been updated to include all contributors
π Chapters
βββββ
Chapter 5: AI Workflow: Corrected errors and improved the clarity of Bravoβs feedback within the chapterβββββ
Chapter 8: AI Training: Bravoβs training example feedback has been improvedβββββ
Chapter 11: AI Acceleration: The AI Acceleration chapter has been updated to reflect feedback from Bravoβββββ
Chapter 16: Responsible AI: Incorporated feedback from Bravo and improved explanations within the chapterβββββ
Chapter 1: Introduction: The introduction has been revised to reflect feedback received from Marcoβββββ
Chapter 6: Data Engineering: Grammar pass fix requests were removedβββββ
Chapter 7: AI Frameworks: Grammar pass fix requests were removed from the chapter
π Jan 07 at 10:19 AM
π Frontmatter
βββββ
Acknowledgements: The acknowledgements section and readme were updated to include a list of contributorsβββββ
Foreword: The wording in the foreword has been refined
π Chapters
βββββ
Chapter 3: DL Primer: The chapter now includes an updated figure caption, additional images and code to clarify the training loop and inference process, and a corrected typo in an equationβββββ
Chapter 4: DNN Architectures: The text was updated with new images and visualization figures and tools were addedβββββ
Chapter 1: Introduction: The distinction between artificial intelligence (AI) and machine learning (ML) is now more clearly defined
π Jan 03 at 04:26 PM
π Frontmatter
βββββ
Acknowledgements: The contributor list has been updated to include all contributors and correct any omissionsβββββ
SocratiQ: Fixed SocratiQ prompt generation issues and improved the user interface for interacting with SocratiQ
π Chapters
βββββ
Chapter 1: Introduction: The definition of machine learning was clarified and examples were updated for improved comprehensionβββββ
Chapter 2: ML Systems: Corrected a typo in the definition of model parallelism and added a TensorFlow example demonstrating data parallelismβββββ
Chapter 6: Data Engineering: Corrected a code snippet in the data ingestion pipeline example and refined the explanation of the ETL processβββββ
Chapter 4: DNN Architectures: Various fixes were implementedβββββ
Chapter 20: Conclusion: Various fixes were implemented
π Jan 02 at 09:06 PM
π Frontmatter
βββββ
Acknowledgements: The contributor list has been updated to include new contributors
π Chapters
βββββ
Chapter 4: DNN Architectures: Removed unnecessary commented text and implemented suggested revisions for clarityβββββ
Chapter 20: Conclusion: Bravoβs suggested edits have been incorporated into the conclusionβββββ
Chapter: Generative Ai: Dead commented-out text has been removed from the chapter
π Jan 01 at 11:42 PM
π Frontmatter
βββββ
Foreword: The foreword now has a smoother flow, corrected sidebar formatting issues, and includes updated text contentβββββ
About: The chapter order has been updated and incorporated feedback from Bravoβββββ
SocratiQ: The chapterβs web formatting was fixed and its content was reorganizedβββββ
Index: The abstract was updatedβββββ
Acknowledgements: The acknowledgements section now includes contributors and the readme has been updated to reflect this
π Chapters
βββββ
Chapter 2: ML Systems: The Mobile ML section was added, system aspects were updated throughout the chapter, and an example system was included to ground conceptsβββββ
Chapter 4: DNN Architectures: The textbook now includes a new section on transformer architectures, an updated overview of the chapter, and fixes to table formatting and referencesβββββ
Chapter 18: Robust AI: The BNN discussion is clearer, the introduction to faults has been reframed, and edge case examples now focus specifically on ML faultsβββββ
About: The bookβs content was reorganized, Bloomβs Taxonomy was incorporated, and the outline was updated to reflect the addition of Chapter 4βββββ
Chapter: Dl Architectures: The chapter was renamed and rewritten to emphasize ML systems, including the addition of Colab notebooks for interactive learningβββββ
Chapter 1: Introduction: The file path was fixed, header formats were changed, and Bravoβs feedback was incorporatedβββββ
Chapter 3: DL Primer: The chapterβs file structure was reorganized, its purpose statement was updated, and issues with Giscus comments were resolvedβββββ
Chapter 5: AI Workflow: A figure illustrating feedback loops was added, a figure reference error was corrected, and the chapterβs purpose was revisedβββββ
Chapter 8: AI Training: The purpose of AI training and its objectives were clarified for better understandingβββββ
Chapter 9: Efficient AI: The purpose of efficient AI techniques was clarifiedβββββ
Chapter 14: On-Device Learning: The purpose of on-device learning was clarifiedβββββ
Chapter 15: Security & Privacy: A duplicate case study was removed from the chapter, a duplicate section was moved to Chapter 14, and the purpose statement was updatedβββββ
Chapter 17: Sustainable AI: The chapterβs purpose was updated and incorporated feedback from Bravoβββββ
Acknowledgements: The acknowledgements section now includes logos and an updated list of contributorsβββββ
SocratiQ: The SocratiQ chapter was reorganized, broken links were repaired, typos were corrected, and an issue brought up by Bravo was resolvedβββββ
Chapter 6: Data Engineering: The purpose of the chapter was updatedβββββ
Chapter 7: AI Frameworks: The purpose of the chapter has been updatedβββββ
Chapter 10: Model Optimizations: The purpose statement for Chapter 10 has been revisedβββββ
Chapter 11: AI Acceleration: The purpose of Chapter 11 has been updatedβββββ
Chapter 12: Benchmarking AI: The purpose statement for benchmarking in AI has been updatedβββββ
Chapter 13: ML Operations: The purpose statement for Chapter 13 has been updatedβββββ
Chapter 16: Responsible AI: The purpose statement for Chapter 16 has been updatedββββ
Chapter 19: AI for Good: The purpose of the chapter has been updatedβββββ
Chapter 20: Conclusion: Some wording was adjusted and a reference to Chapter 4 was added
π§βπ» Labs
βββββ
Lab: Raspi: The lab now includes a new VLM lab and the grid table formatting has been updatedβββββ
Lab: Pi Vision Language Models: A new lab exploring Vision Language Models (VLMs) has been addedβββββ
Lab: Labs Overview: A VLM has been added to the main table
π Nov 19 at 12:23 PM
π Chapters
βββββ
SocratiQ: The text was updated and an AI podcast was addedβββββ
Acknowledgements: The contributor list has been updated to include new contributors
π Nov 19 at 01:57 AM
π Chapters
βββββ
Chapter 15: Security & Privacy: This chapter now includes machine unlearning, a revised table order, and a new federated learning case study replacing the previous oneβββββ
Chapter 16: Responsible AI: The chapter now includes summarized policies, a revised figure with a clearer explanation, and formatting adjustments for improved readabilityβββββ
Chapter 17: Sustainable AI: The chapterβs grammar was refined, a new image illustrating the water footprint was added, and the LCA figure was updatedβββββ
Chapter 19: AI for Good: The chapter now includes grammatical improvements and a discussion motivating the use of TinyMLβββββ
Acknowledgements: The acknowledgements section and readme were updated to include a list of contributorsβββββ
SocratiQ: Added .png support for gif images in PDF builds, updated the widget suggestions blog, and changed the variable name widget_access to socratiq
π Nov 16 at 06:09 PM
π Chapters
βββββ
Chapter 16: Responsible AI: The explanation of a table has been clarifiedβββββ
Acknowledgements: The contributor list has been updated and the preface material reorganizedβββββ
About: The βAboutβ file now has a corrected relative path and reorganized contentβββββ
Chapter 1: Introduction: A broken reference link was fixed
π Nov 15 at 09:09 PM
π Chapters
βββββ
Chapter 13: ML Operations: The chapter now features reorganized content with grouped topics, removed redundancies, connected roles sections for clarity, a restructured data management section, and an updated introduction styled as an overviewβββββ
Chapter 2: ML Systems: The Introduction section has been replaced with an Overviewβββββ
Chapter 5: AI Workflow: The roles sections throughout the AI workflow chapter have been connected for better flow and understandingβββββ
Chapter 14: On-Device Learning: The introduction section was replaced with an overview and the language was simplified for improved clarityβββββ
Chapter 16: Responsible AI: The chapter now features improved definitions and an Overview section replacing the Introductionβββββ
Chapter 19: AI for Good: The Introduction section has been replaced with an Overviewβββββ
Chapter 1: Introduction: Fixed definition formatting to be normal font and addressed style consistency errorsβββββ
Chapter 6: Data Engineering: The Introduction section was replaced with an Overview sectionβββββ
Chapter 7: AI Frameworks: The Introduction section has been replaced with an Overview sectionβββββ
Chapter 8: AI Training: The Introduction section has been replaced with an Overview sectionβββββ
Chapter 9: Efficient AI: The Introduction section was replaced with an Overview sectionβββββ
Chapter 10: Model Optimizations: The Introduction section was replaced with an Overview sectionβββββ
Chapter 11: AI Acceleration: The Introduction section has been replaced with an Overviewβββββ
Chapter 12: Benchmarking AI: The chapter now features an Overview instead of an Introductionβββββ
Chapter 18: Robust AI: The Introduction section has been replaced with an Overview sectionβββββ
Chapter 15: Security & Privacy: The Introduction section has been replaced with an Overviewβββββ
Chapter 20: Conclusion: The Introduction section has been replaced with an Overview sectionβββ
Chapter 3: DL Primer: The Introduction section has been replaced with an Overviewβββ
Chapter 17: Sustainable AI: The Introduction section was replaced with an Overview
π§βπ» Labs
βββββ
Lab: Raspberry Pi Setup: The introduction has been replaced with an overview and the language has been simplified for improved clarityβββββ
Lab: Pi Large Language Models: The Introduction section has been replaced with an Overviewβββββ
Lab: Arduino Setup: The Introduction section was replaced with an Overview sectionβββββ
Lab: Arduino Image Classification: The Introduction section has been replaced with an Overview sectionβββββ
Lab: Arduino Object Detection: The Introduction section was replaced with an Overview sectionβββββ
Lab: Arduino Keyword Spotting: The Introduction section has been replaced with an Overview sectionβββββ
Lab: Arduino Motion Classification: The introduction section has been replaced with an overviewβββββ
Lab: XIAO Setup: The Introduction section has been replaced with an Overviewβββββ
Lab: XIAO Image Classification: The Introduction section has been replaced with an Overview sectionβββββ
Lab: XIAO Object Detection: The Introduction section was replaced with an Overview sectionβββββ
Lab: XIAO Keyword Spotting: The Introduction section has been replaced with an Overview sectionβββββ
Lab: XIAO Motion Classification: The Introduction section has been replaced with an Overview sectionβββββ
Lab: Pi Image Classification: The Introduction section has been replaced with an Overviewβββββ
Lab: Pi Object Detection: The Introduction section has been replaced with an Overviewβββββ
Lab: Kws Feature Eng: The Introduction section has been replaced with an Overview sectionβββββ
Lab: Dsp Spectral Features Block: The Introduction section has been replaced with an Overview
π Nov 15 at 11:10 AM
π Chapters
βββββ
Chapter 1: Introduction: The definition of machine learning was updated, case studies were added with multimedia links, and the text flow and wording were improved for better clarityβββββ
Chapter 12: Benchmarking AI: The chapter content has been streamlined by removing labs and reworking examples. A new section exploring energy in AIβs historical context was added, along with the relocation of measurement informationβββββ
Chapter 14: On-Device Learning: The chapter content was reorganized to improve clarity, with a focus on explaining pruning and IID concepts within the context of on-device learning, restructuring the lifelong learning section, and differentiating on-device learning from federated learningβββββ
Chapter 15: Security & Privacy: Added labs to the chapter, updated security content, and renamed images to enhance privacy and securityβββββ
Chapter 14: On-Device Learning: The on-device learning chapter now includes new labs and core folders, along with updated contentβββββ
Chapter 3: DL Primer: The DL Primer chapter was updated with new content and labs and core folders were createdβββββ
Chapter 2: ML Systems: The chapter now includes labs and a core folder, features updated ML systems content, revised learning objectives, and an introduction that encompasses a broader scope than just embedded systemsβββββ
Chapter 2: ML Systems: The labs portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 3: DL Primer: The labs portion has been removed from the chapters and moved into a new βlabsβ folder, while the core content is now in a βcoreβ folderβββββ
Chapter 5: AI Workflow: The labs portion has been removed from the chapters and moved into a new βlabsβ folder, while the core content is now in a βcoreβ folderβββββ
Chapter 6: Data Engineering: The labs portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 7: AI Frameworks: Labs were removed from the chapters and new βlabsβ and βcoreβ folders were created along with the addition of a referenceβββββ
Chapter 8: AI Training: The labs portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 9: Efficient AI: The lab portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 10: Model Optimizations: The labs portion has been removed from the chapter content and moved to a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 11: AI Acceleration: The labs portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 13: ML Operations: The ML Operations chapter now has a dedicated βlabsβ folder for practical exercises and incorporates feedback from Bravoβββββ
Chapter 18: Robust AI: The labs portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 15: Security & Privacy: The chapter now excludes lab exercises and has been reorganized into βlabsβ and βcoreβ foldersβββββ
Chapter 16: Responsible AI: The labs portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 17: Sustainable AI: The labs portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Chapter 19: AI for Good: The labs portion has been removed from the chapters and moved into a new βlabsβ folder within the βcoreβ folderβββββ
Acknowledgements: The βAcknowledgementsβ chapter now has dedicated folders for labs and core contentβββββ
SocratiQ: A draft of the SocratiQ bot and its QMD file were createdβββββ
Chapter 19: AI for Good: A labs folder was created and the AI4Good content was updatedβββββ
Chapter 18: Robust AI: The textbook now includes a dedicated βlabsβ folder and updated content within the Robust AI chapterβββββ
Chapter 17: Sustainable AI: A labs folder was created and the sustainable AI content was updatedβββββ
Chapter 16: Responsible AI: A labs folder was created and the responsibleAI content was updatedβββββ
Chapter 13: ML Operations: The ML Operations chapter now includes a labs folder and a core folder, and the MLops content has been updatedβββββ
Chapter 12: Benchmarking AI: Labs and core folders were created and benchmarking content was updatedβββββ
Chapter 11: AI Acceleration: A labs folder was created and the AI hardware section was updatedβββββ
Chapter 10: Model Optimizations: Labs and core folders were created, the βdevβ branch was merged, suggested fixes were implemented, and the optimization content was updatedβββββ
Chapter 9: Efficient AI: The βEfficient AIβ chapter now includes a labs and core folder, along with updated efficiency informationβββββ
Chapter 8: AI Training: A labs folder was created and the training material was updatedβββββ
Chapter 7: AI Frameworks: The AI Frameworks chapter now includes dedicated labs and core folders, along with updated information on various machine learning frameworksβββββ
Chapter 6: Data Engineering: The chapter now includes dedicated labs and core folders, along with updated data engineering content and a revised pathβββββ
Chapter 5: AI Workflow: The AI Workflow chapter now includes a labs folder and a core folder, and the workflow content has been updatedβββββ
Chapter 1: Introduction: The introduction was updated with revised text and new lab and core folders were createdβββββ
SocratiQ: A draft of the SocratiQ bot has been created
π§βπ» Labs
βββββ
Lab: Labs: The labs were restructured for clarity, documentation was enhanced, and icon usage was adjusted to support PDF buildsβββββ
Lab: Pi Image Classification: The lab now includes notes about large language models and other general machine learning concepts, and has been updated to include Raspberry Pi supportβββββ
Lab: Arduino Keyword Spotting: Corrected code examples for better functionality, clarified instructions for easier understanding, and updated links to ensure accuracy and relevanceβββββ
Lab: Raspi: The formatting of starred text was standardized and the content within raspi.qmd was updatedβββββ
Lab: Raspberry Pi Setup: Corrected the use of colons in code snippets and incorporated notes about large language models and general machine learning conceptsβββββ
Lab: Pi Object Detection: Fixed output formatting issues and improved code readability in the object detection labβββββ
Lab: Pi Large Language Models: A lab for SLMs has been added and some text formatting issues have been correctedβββββ
Lab: Labs Overview: The lab overview has been restructured to address issues related to PARTβββββ
Lab: Nicla Vision: Corrected the use of β: β and β :β in code block text to ensure consistencyβββββ
Lab: Xiao Esp32S3: Corrected the formatting of text using asterisks for emphasisβββββ
Lab: XIAO Setup: Corrected the formatting of text elements to ensure consistencyβββββ
Lab: XIAO Keyword Spotting: Corrected the use of colons in code examples for consistency
π Sep 20 at 07:26 AM
π Chapters
βββββ
Chapter 19: AI for Good: All chapters have been revised and references to figures and other content have been correctedβββββ
Chapter 11: AI Acceleration: Character formatting was corrected, figure references were fixed, and all chapters are now completeβββββ
Chapter 7: AI Frameworks: Figure references were fixed and all chapters were revisedβββββ
Chapter 3: DL Primer: Fixed a broken link to a video and corrected instances of ββ being used instead of β, along with completing revisions for all chaptersβββββ
Chapter 6: Data Engineering: Character formatting was corrected, formatting was improved, and figure references were addedβββββ
Chapter 1: Introduction: Removed references to embedded AI and fixed broken figure references throughout the chapterβββββ
Chapter 9: Efficient AI: Figure references were fixed and all chapters are now completeβββββ
Chapter 14: On-Device Learning: References throughout the chapter were corrected and a path issue was resolvedβββββ
Chapter 5: AI Workflow: References and figure citations were corrected throughout the chapterβββββ
Chapter 13: ML Operations: Figure references were fixed and all chapters were updatedβββββ
Chapter 15: Security & Privacy: Figure references were fixed and merge conflicts were resolved in the chapterβββββ
Chapter 12: Benchmarking AI: The chapterβs formatting was improved, some figures were removed, and merge conflicts were resolvedβββββ
Chapter 2: ML Systems: Figure references were corrected and all chapters are now completeβββββ
Chapter 10: Model Optimizations: Corrected single quotes to apostrophesβββββ
Chapter 8: AI Training: Corrected instances where single quotation marks were used inconsistently with double quotation marksβββββ
Chapter 17: Sustainable AI: Figure references were corrected and typos in the sustainability section were fixed
π§βπ» Labs
βββββ
Lab: Arduino Object Detection: The Arduino object detection lab now includes fixes for code issues and adjustments to the output formatβββββ
Lab: XIAO Setup: Fixes were implemented to improve the XIAO ESP32S3 setup processβββββ
Lab: XIAO Image Classification: The image classification lab now has corrected output formattingβββββ
Lab: XIAO Object Detection: The lab received fixes contributed by BravoBaldoβββββ
Lab: XIAO Keyword Spotting: Fixes were implemented to improve the accuracy and efficiency of the XIAO keyword spotting implementationβββββ
Lab: Raspberry Pi Setup: Character formatting was corrected and additional files were added to the lab setupβββββ
Lab: Lab Setup: Lab setup instructions have been corrected for accuracy and clarityβββββ
Lab: Arduino Motion Classification: The lab received fixes from BravoBaldoβββββ
Lab: XIAO Motion Classification: An image was fixedβββββ
Lab: Raspi: Fixes were implemented by BravoBaldoβββββ
Lab: Pi Image Classification: Character formatting and typos were correctedβββββ
Lab: Pi Object Detection: Corrected typos throughout the lab
π Sep 12 at 10:16 AM
π Chapters
βββββ
Chapter 13: ML Operations: The chapter content has been revised based on feedback from Baldoβββββ
Chapter 20: Conclusion: The conclusion has been revised based on feedbackβββββ
Chapter 19: AI for Good: Several fixes were implemented throughout the chapterβββββ
Chapter 18: Robust AI: The Robust AI chapter has been fixed thanks to contributions from (BravoBaldo?)βββββ
Chapter 17: Sustainable AI: The indentation of a quote was fixed and formatting was improved throughout the chapter
π§βπ» Labs
βββββ
Lab: Pi Object Detection: The Object Detection Lab has been uploaded and includes instructions for running it on a Raspberry Piβββββ
Lab: Pi Image Classification: A link and some typos were corrected
π Sep 06 at 07:18 AM
π Chapters
βββββ
Chapter 16: Responsible AI: The bibliography and text were corrected for accuracy
π Sep 04 at 07:32 PM
π Chapters
βββββ
Chapter 11: AI Acceleration: The chapter includes grammar corrections and improved explanations for clarityβββββ
Chapter 9: Efficient AI: The explanations in Chapter 9 have been refined for better clarityβββββ
Chapter 1: Introduction: Captions for even-numbered pages have been correctedβββββ
Chapter 15: Security & Privacy: The chapter contains grammar corrections and bug fixesβββββ
Chapter 19: AI for Good: Grammar issues were corrected throughout the chapterβββββ
Chapter 12: Benchmarking AI: The chapter contains grammar fixes for improved clarityβββββ
Chapter 20: Conclusion: The conclusion chapter has been revised for improved grammar and clarityβββββ
Chapter 6: Data Engineering: Grammar errors were corrected throughout the chapterβββββ
Chapter 3: DL Primer: Grammar errors were corrected throughout the chapterβββββ
Chapter 7: AI Frameworks: Grammar errors were corrected throughout the chapterβββββ
Chapter 2: ML Systems: Grammar errors were corrected throughout the chapterβββββ
Chapter 14: On-Device Learning: Grammar errors were corrected throughout the chapterβββββ
Chapter 13: ML Operations: Grammar errors were corrected throughout the chapterβββββ
Chapter 10: Model Optimizations: Grammar errors were corrected throughout Chapter 10βββββ
Chapter 16: Responsible AI: Grammar issues were corrected throughout the chapterβββββ
Chapter 18: Robust AI: Grammar errors were corrected throughout the chapterβββββ
Chapter 17: Sustainable AI: Grammar errors were corrected throughout the chapterβββββ
Chapter 8: AI Training: Grammar errors were corrected throughout the chapter
π§βπ» Labs
βββββ
Lab: Arduino Image Classification: The lab now contains grammar corrections for improved readabilityβββββ
Lab: Kws Feature Eng: Grammar errors were corrected throughout the lab
π Sep 02 at 08:19 PM
π Chapters
βββββ
Chapter 13: ML Operations: A section on model serving was added and the content was improved along with fixing some mistakesβββββ
Chapter 11: AI Acceleration: The chapter now includes a table fix, more student-friendly explanations of hardware design principles, and an introductionβββββ
Chapter 2: ML Systems: A dangling sentence was corrected
π§βπ» Labs
βββββ
Lab: Raspberry Pi Setup: The Raspberry Pi setup instructions were updated and additional files were includedβββββ
Lab: Pi Image Classification: Files were added to the lab
π Aug 29 at 11:14 PM
π Chapters
βββββ
Chapter 14: On-Device Learning: The chapter content has been revised to incorporate feedback from (BravoBaldo?)βββββ
Chapter 13: ML Operations: The chapter received fixes based on feedback from BravoBaldo
π§βπ» Labs
βββββ
Lab: Labs: Resolved an issue with merging tablesβββββ
Lab: Pi Image Classification: Files were added to the labβββββ
Lab: Kws Feature Eng: Formatting issues were fixed
π Aug 27 at 12:28 PM
π Chapters
βββββ
Chapter 9: Efficient AI: Duplicate information was removed between chapters 8 and 9, background about floating point representation was added, and explanations of structure importance methods were correctedβββββ
Chapter 10: Model Optimizations: Duplicate information was removed between chapters 8 and 9, the knowledge distillation explanation was improved, and the challenges were adjusted to be less repetitiveβββββ
Chapter 7: AI Frameworks: The AI Frameworks chapter now has corrected links and improved table formattingβββββ
Chapter 15: Security & Privacy: The Power Attack and Side-Channel Attack sections were edited and broken links were fixedβββββ
Chapter 11: AI Acceleration: This update fixes several issues including broken links, inaccurate information about qbits, hyphen errors, duplicate titles, and an incomplete sentenceβββββ
Chapter 12: Benchmarking AI: Fixes were implemented throughout the chapterβββββ
Chapter 13: ML Operations: Minor wording changes were made for improved clarity and concisenessβββββ
Chapter 17: Sustainable AI: Broken links within the chapter have been fixed
π§βπ» Labs
βββββ
Lab: Xiao Esp32S3: Table formatting for grid tables has been fixed
π Aug 22 at 11:13 AM
π Chapters
βββββ
Chapter 19: AI for Good: A new section on AI for climate change mitigation was added, the disaster response case study was updated, and ethical considerations in AI for good were discussedβββββ
Chapter 11: AI Acceleration: A new section on systolic array architectures was added, the discussion of tensor cores was updated, and example code for matrix multiplication on a TPU was includedβββββ
Chapter 17: Sustainable AI: A new section on ethical considerations in AI development was added, existing content on bias mitigation techniques was updated, and real-world case studies of sustainable AI practices were included
π§βπ» Labs
βββββ
Lab: Labs: Lab files were added to the textbookβββββ
Lab: Raspi: Files were added to the Raspi labβββββ
Lab: Raspberry Pi Setup: Files were added to the Raspberry Pi Setup lab
π Aug 21 at 09:47 PM
π Chapters
βββββ
Dsp Spectral Features Block: Removed dead code from the chapterβββββ
Lab: Arduino Image Classification: Dead code was removed from the labβββββ
Chapter 10: Model Optimizations: Typos were corrected throughout the chapterβββββ
Chapter 6: Data Engineering: Typos were correctedβββββ
Chapter 7: AI Frameworks: Typos were fixedβββββ
Chapter 11: AI Acceleration: Typos were fixedβββββ
Chapter 14: On-Device Learning: Typos were correctedβββββ
Chapter 13: ML Operations: Typos were correctedβββββ
Chapter 15: Security & Privacy: Typos were fixedβββββ
Chapter 8: AI Training: Inconsistent bold text has been removed throughout the chapterβββββ
Chapter 2: ML Systems: A minor typo was corrected
π§βπ» Labs
βββββ
Lab: Pi Image Classification: This lab introduces a basic image classification pipeline using a Raspberry Piβββββ
Lab: Pi Object Detection: This lab introduces object detection using a Raspberry Piβββββ
Lab: Labs: The lab section now includes a fixed table format and an initial version of a Raspberry Pi labβββββ
Lab: Raspi: This lab introduces a Raspberry Pi-based machine learning projectβββββ
Lab: Raspberry Pi Setup: This lab now includes initial instructions for setting up a Raspberry Pi for machine learning tasksβββββ
Lab: Pi Large Language Models: This lab introduces a basic implementation of a large language model on a Raspberry Piβββββ
Lab: Lab Setup: This lab now includes initial instructions for setting up a Raspberry Pi environment
π Aug 15 at 03:57 PM
π Chapters
βββββ
Chapter 15: Security & Privacy: Table references were fixed for accuracyβββββ
Chapter 11: AI Acceleration: Table references were fixed for accuracyβββββ
Chapter 13: ML Operations: Table references were fixed
π Aug 15 at 03:41 PM
π Chapters
βββββ
Chapter 6: Data Engineering: Implemented pivotal fixes and enhancements to improve the clarity and effectiveness of data engineering explanationsβββββ
Chapter 10: Model Optimizations: Several pivotal fixes and enhancements were made to improve clarity and accuracy of the contentβββββ
Chapter 18: Robust AI: Citation references were fixed and tables now have striped and hover stylesβββββ
Chapter 13: ML Operations: Tables now have striped and hover styles, centering has been fixed, and the grid table has been updatedβββββ
Chapter 15: Security & Privacy: The table in this chapter has been updated to a grid format and several fixes have been implementedβββββ
Chapter 8: AI Training: A broken Colab link was fixed, table formatting was updated, and some minor text edits were madeβββββ
Chapter 19: AI for Good: The AI for Good chapter has been enhancedβββββ
Chapter 12: Benchmarking AI: The chapter now includes fixes, utilizes improved language for clarity, and delves deeper into various benchmarking techniquesβββββ
Chapter 3: DL Primer: The chapter received several enhancements and bug fixesβββββ
Chapter 9: Efficient AI: The chapter contains fixes and enhancements based on user feedback and deeper exploration of conceptsβββββ
Chapter 7: AI Frameworks: Implemented fixes and enhancements related to delve and utilization within the framework discussionsβββββ
Chapter 11: AI Acceleration: The grid table in the chapter has been updated and several errors have been fixedβββββ
Lab: Arduino Image Classification: The Arduino image classification lab has been enhancedβββββ
Chapter 1: Introduction: The introduction has been updated with fixes related to delve integrationβββββ
Chapter 2: ML Systems: Implemented pivotal fixes and enhanced utilization within the chapterβββββ
Chapter 14: On-Device Learning: The chapter now includes a grid table and has been corrected for errorsβββββ
Chapter 16: Responsible AI: The chapter content is now presented in a grid table formatβββββ
Chapter 17: Sustainable AI: The chapter includes fixes and enhancements related to delve utilizationβββββ
Chapter 5: AI Workflow: The AI Workflow chapter received several enhancements and bug fixes to improve clarity and accuracy
π§βπ» Labs
βββββ
Lab: Arduino Image Classification: The Arduino image classification code has been enhanced and fixes have been implemented for issues within the labβββββ
Lab: XIAO Image Classification: Delve fixes were implementedβββββ
Lab: XIAO Keyword Spotting: The lab now utilizes
π Aug 15 at 07:22 AM
π Chapters
βββββ
Chapter 8: AI Training: The chapter now includes a discussion on regularization techniques and hyperparameter search methods, consolidates information about common training pitfalls, and updates the notation used for neural networksβββββ
Chapter 9: Efficient AI: The Efficient AI chapter was updated with changes incorporated from the βdevβ branchβββββ
Chapter 7: AI Frameworks: Typos were corrected throughout the chapter
π Aug 06 at 09:39 PM
π Chapters
βββββ
Chapter 7: AI Frameworks: The chapter content was updated to focus on advanced features while removing the federated learning section. Table formatting was improved for better readability and consistencyβββββ
Dsp Spectral Features Block: Image width issues affecting PDF rendering have been fixedβββββ
Lab: Arduino Image Classification: Image width issues were fixed for PDF rendering, redundant underlines were removed, and remaining broken video links were correctedβββββ
Chapter 13: ML Operations: The chapter now features corrected URL links, updated table formatting for a grid view, and consistent βSourceβ attribution with revised formattingβββββ
Chapter 18: Robust AI: Tables in this chapter now use grid formatting and are left-aligned for better readability, and source citations have been updatedβββββ
Chapter 5: AI Workflow: Tables now use grid formatting and are left-aligned with markdown, incorporating student feedbackβββββ
Chapter 3: DL Primer: Fixed all broken URL links in the chapter, updated credit information to βSource:β, and improved table formatting for consistencyβββββ
Chapter 6: Data Engineering: The chapter now has consistent source citations and includes a new Wake Vision Colab exerciseβββββ
Chapter 15: Security & Privacy: The privacy and security section was edited and broken links were fixedβββββ
Chapter 19: AI for Good: All broken URL links were fixed and credit source formatting was updated for consistencyβββββ
Chapter 11: AI Acceleration: All broken URL links were fixed and credit source formatting was updated for consistencyβββββ
Chapter 14: On-Device Learning: All broken URL links were fixed, table formatting was updated, and the βCreditβ section was renamed to βSourceββββββ
Chapter 16: Responsible AI: All broken URL links were fixed, credit sources were updated with consistent formatting, and HTML + PDF builds were added for Edward Tufteβββββ
Chapter 8: AI Training: All broken URL links were fixed, credit source formatting was updated to be consistent, and grid tables with left-aligned markdown formatting were implementedβββββ
Chapter 9: Efficient AI: Grid tables were added to the chapter, all tables are now left-aligned, and image paths and figure IDs were updated for consistencyβββββ
Chapter 2: ML Systems: Implemented grid tables, aligned all tables with markdown formatting, standardized source formatting, and added an HTML + PDF build based on Edward Tufteβs styleβββββ
Chapter 10: Model Optimizations: Implemented grid tables for better presentation, aligned all tables with markdown formatting, and added in-text citations for sourcesβββββ
Chapter 12: Benchmarking AI: Credit attributions were updated and formatting was made consistent throughout the chapterβββββ
Chapter 17: Sustainable AI: Source citations were updated and formatting was standardized for consistency across the document; additionally, HTML and PDF builds were createdβββββ
Chapter 1: Introduction: The textbook now has HTML and PDF output formats
π§βπ» Labs
βββββ
Lab: Nicla Vision: Tables are now left-aligned and credit information is updated with consistent formattingβββββ
Lab: Arduino Setup: Image width issues for PDF rendering were fixed and redundant underlines were removedβββββ
Lab: Arduino Image Classification: Image width issues were fixed for PDF rendering, redundant formatting was removed, and remaining broken video links were correctedβββββ
Lab: Arduino Object Detection: Image width issues were fixed for PDF rendering and all broken video links were repairedβββββ
Lab: Arduino Keyword Spotting: Image width issues were fixed to improve PDF rendering and all broken URL links were correctedβββββ
Lab: Arduino Motion Classification: Image width issues affecting PDF rendering have been fixedβββββ
Lab: XIAO Setup: Image width issues affecting PDF rendering have been fixedβββββ
Lab: XIAO Image Classification: Image width issues affecting PDF rendering have been fixedβββββ
Lab: XIAO Object Detection: Image width issues affecting PDF rendering have been fixedβββββ
Lab: XIAO Keyword Spotting: Image width issues in PDFs were fixed and broken links caused by formatting were resolvedβββββ
Lab: XIAO Motion Classification: Image width issues affecting PDF rendering have been fixedβββββ
Lab: Dsp Spectral Features Block: Image width issues affecting PDF rendering have been fixedβββββ
Lab: Xiao Esp32S3: The credit section was updated to βSource:β and formatting was corrected for consistencyβββββ
Lab: Shared: Tables in markdown formatting are now left alignedβββββ
Lab: Kws Feature Eng: Image widths were fixed to ensure proper rendering in PDF format
π Jun 25 at 07:01 AM
π Chapters
βββββ
Chapter 3: DL Primer: The link for video 3.1 has been corrected
π Jun 20 at 05:33 PM
π Chapters
βββββ
Chapter 2: ML Systems: The chapter now includes corrections to a broken reference and incorporates feedback from students
π§βπ» Labs
βββββ
Lab: Shared: Broken links were fixed
π Jun 19 at 08:54 AM
π Chapters
βββββ
Object Detection Fomo: Labs have been integrated into the Object Detection Fomo chapterβββββ
Chapter 12: Benchmarking AI: The chapter now includes an MLPerf training progress figure and incorporates updates from Colbyβs revisions while resolving reference build problemsβββββ
Chapter 11: AI Acceleration: Citation formatting was changed from parentheses to brackets, MD lint fixes were implemented, and a link to Googleβs Edge TPU website was addedβββββ
Chapter 1: Introduction: The introduction material was updated and the foreword content was removed to improve clarity and focusβββββ
Chapter 2: ML Systems: The content of the chapter has been improved based on feedback and data reviewβββββ
Chapter 6: Data Engineering: Citation formatting was changed from parentheses to square brackets and minor code style issues were addressedβββββ
Chapter 10: Model Optimizations: Citation formatting was changed from parentheses to brackets and several typos were correctedβββββ
Chapter 18: Robust AI: Citation formatting was changed from parentheses to brackets and markdown linting issues were addressedβββββ
Acknowledgements: The acknowledgements were updated with MD lint fixes and some comments were disabled on specific pagesβββββ
Chapter 19: AI for Good: Applied Markdown linting fixes for improved formatting consistencyβββββ
Chapter 20: Conclusion: Applied Markdown linting fixes for consistency and readabilityβββββ
Chapter 3: DL Primer: Redundancy was removed, a formatting issue was fixed, and several typos were correctedβββββ
Chapter 9: Efficient AI: Video references were added and minor formatting issues were correctedβββββ
Chapter 7: AI Frameworks: The chapter contains a batch of typo and format fixesβββββ
Lab: Arduino Image Classification: The lab notebook underwent code style and formatting improvements using MD lintβββββ
Chapter 14: On-Device Learning: Applied Markdown linting fixes for improved formatting and consistencyβββββ
Chapter 13: ML Operations: The chapterβs Markdown code underwent syntax and style checks for consistencyβββββ
Chapter 15: Security & Privacy: The chapterβs headers were corrected for consistency and minor code style issues were addressedβββββ
Chapter 16: Responsible AI: The chapterβs Markdown formatting has been improved for consistency and readabilityβββββ
Chapter 17: Sustainable AI: The chapterβs Markdown code was cleaned up for consistency and readabilityβββββ
Chapter 8: AI Training: The chapter contains a batch of typo and format fixesβββββ
Chapter 5: AI Workflow: The Markdown code was cleaned up using a linting toolβββββ
Dsp Spectral Features Block: Resources were fixed and the title was slightly modifiedβββββ
Generative Ai: Several instances of wording were refined for clarity
π§βπ» Labs
βββββ
Lab: Labs: The lab section was reorganized, the overview was updated, a table was transposed and updated, and labs were integrated into the contentβββββ
Lab: Nicla Vision: The lab now has a corrected build process, includes KWS, features improved introductory text, updated images, and a restructured folderβββββ
Lab: Arduino Image Classification: This update fixes resource links, integrates the Arduino labs into the curriculum, and adds all necessary Arduino lab filesβββββ
Lab: Arduino Setup: Resources were updated, elements were renamed, and the setup was integrated into the lab environmentβββββ
Lab: Arduino Object Detection: Resource links were fixed and the object detection lab was integrated into the existing labs sectionβββββ
Lab: Arduino Keyword Spotting: Resource links were fixed, code examples were improved, and grammar was correctedβββββ
Lab: Arduino Motion Classification: The lab now has corrected grammar and improved content placementβββββ
Lab: Xiao Esp32S3: The lab now has a restructured folder with fixed build errors, an image credit, and improved introductory textβββββ
Lab: XIAO Setup: Resources were fixed, SEEED labs were imported, and some elements were renamedβββββ
Lab: XIAO Image Classification: The lab now imports SEEED labs and integrates them into the existing lab structure, with resource fixes implementedβββββ
Lab: XIAO Object Detection: The lab now includes MD lint fixes, resource corrections, and integration with SEEED labsβββββ
Lab: XIAO Keyword Spotting: Resources were fixed, SEEED labs were imported and integrated into the lab exercisesβββββ
Lab: XIAO Motion Classification: The lab now includes fixed resources, a link to an internal document, and integrates with SEEED labsβββββ
Lab: Shared: Added an overview of the shared labs sectionβββββ
Lab: Kws Feature Eng: Resources were fixed, minor tweaks were made, and the lab was integrated into the existing structureβββββ
Lab: Dsp Spectral Features Block: The labβs title was slightly adjusted and it is now integrated into other lab sectionsβββββ
Lab: Lab Setup: Added getting started content and updated the overview section with a placeholder for detailed information
π Jun 11 at 04:08 PM
π Chapters
βββββ
Chapter 18: Robust AI: The chapter now includes video callouts, reorganized exercise callouts, updated references and links, an expanded general description, and information about Bayesian Neural Networksβββββ
Chapter 11: AI Acceleration: Video callouts were added to the chapter along with end-of-section resources, and spacing and formatting issues were correctedβββββ
Chapter 19: AI for Good: Video callouts were added to the chapter and exercise callout blocks were folded for improved visual presentationβββββ
Chapter 12: Benchmarking AI: Video callouts were added to the chapter, a previous formatting issue was fixed, and exercise callout blocks were reorganized for better visual appealβββββ
Chapter 6: Data Engineering: Video callouts were added and all exercise callout blocks were folded for improved aestheticsβββββ
Chapter 3: DL Primer: Video callouts and end-of-section resources were added to the chapterβββββ
Chapter 9: Efficient AI: Video callouts and end-of-section resources were added to the chapterβββββ
Chapter 7: AI Frameworks: Video callouts were added and all exercise callout blocks were folded for improved aestheticsβββββ
Chapter 2: ML Systems: Video callouts were added and exercise callout blocks were folded for improved visual presentationβββββ
Chapter 14: On-Device Learning: Video callouts were added to the chapter and exercise callout blocks were folded for improved visual appealβββββ
Chapter 13: ML Operations: Video callouts were added to the chapter and exercise callout blocks were folded for improved visual appealβββββ
Chapter 10: Model Optimizations: Video callouts were added and exercise callout blocks were folded for improved aestheticsβββββ
Chapter 15: Security & Privacy: Video callouts were added and exercise callout blocks were folded for improved visual presentationβββββ
Chapter 16: Responsible AI: Video callouts and end-of-section resources were added to the chapterβββββ
Chapter 17: Sustainable AI: Video callouts were added and all exercise callout blocks were folded for improved aestheticsβββββ
Chapter 8: AI Training: Video callouts were added to the chapter, exercise callout blocks were reorganized for better visual appeal, and a table rendering issue was fixedβββββ
Chapter 5: AI Workflow: Video callouts were added to the chapter and a previous formatting error with .callout was fixedβββββ
Generative Ai: Added and tweaked coming soon text about generative AI
π Jun 01 at 01:11 PM
π Chapters
βββββ
Chapter 19: AI for Good: The Colab badge was repaired, the βcoming soonβ section now uses bullets, and the slide notes use the default format for better PDF outputβββββ
Chapter 12: Benchmarking AI: The Colab badge was fixed, the βcoming soonβ section was updated with bullets, and the default note for slides was implemented for better PDF renderingβββββ
Chapter 6: Data Engineering: The Colab badge was fixed, the βcoming soonβ section was updated with bullets, and minor markdown issues were corrected in the text and URL highlightingβββββ
Chapter 3: DL Primer: The Colab badge was fixed, the βcoming soonβ section now uses bullets, and the default note for slides was changed for better PDF renderingβββββ
Chapter 7: AI Frameworks: The Colab badge was fixed, the βcoming soonβ section now uses bullets, and the default note for slides is updated for better PDF renderingβββββ
Chapter 11: AI Acceleration: The Colab badge was fixed, the βcoming soonβ section was updated with bullets, and the default note for slides was changed for better PDF renderingβββββ
Chapter 2: ML Systems: Resolved Colab badge display errors, revised the βcoming soonβ section with bullets, and ensured slides rendered properly in PDF formatβββββ
Chapter 14: On-Device Learning: The Colab badge was fixed, the βcoming soonβ section was updated to use bullets, and slide note formatting was changed for better PDF renderingβββββ
Chapter 13: ML Operations: The Colab badge was fixed, the βcoming soonβ section was updated to use bullets, and the default note for slides was changed to render better in PDFβββββ
Chapter 10: Model Optimizations: The Colab badge was fixed, the βcoming soonβ section now uses bullets, and the default note for slides was changed for better PDF renderingβββββ
Chapter 15: Security & Privacy: The Colab badge was fixed, the βcoming soonβ section was updated with bullets, and the default note for slides was changed to improve PDF renderingβββββ
Chapter 18: Robust AI: Resolved Colab badge and rendering problems, implemented (exr?)- for Colabs, and optimized slide display for PDFsβββββ
Chapter 17: Sustainable AI: The Colab badge was fixed, the βcoming soonβ section was updated with bullets, and the default note for slides was changed for better PDF renderingβββββ
Chapter 8: AI Training: The Colab badge was fixed, the βcoming soonβ section was updated with bullets, and formatting was improved for labs, exercises, and slidesβββββ
Chapter 9: Efficient AI: Fixed rendering problems, corrected some headers, and set a default note for slides to ensure proper PDF outputβββββ
Chapter 16: Responsible AI: The coming soon section was updated with bullets, default notes were applied to slides for better PDF rendering, and formatting was adjusted in labs, exercises, and slidesβββββ
Chapter 5: AI Workflow: The coming soon section now uses bullets, the slide default note was changed for better PDF rendering, and formatting was adjusted in labs, exercises, and slidesβββββ
Chapter 1: Introduction: Reference links were reintroduced and the introduction sectionβs grammar and readability were enhancedβββββ
Generative Ai: Fixed rendering problems in the chapter
π May 26 at 03:41 PM
π Chapters
βββββ
Chapter 18: Robust AI: This update includes a new resources section, incorporates feedback for improved clarity, and addresses several figure reference and formatting issuesβββββ
Chapter 10: Model Optimizations: The chapter now includes videos, updated exercises, and additional slidesβββββ
Chapter 20: Conclusion: The conclusion section was updated and a cover image was added to the fileβββββ
Chapter 3: DL Primer: This update includes added videos, an updated Data Diversity and Quality section, and captions for all tablesβββββ
Chapter 14: On-Device Learning: This chapter now includes short captions for videos, additional Colab exercises, and an updated conclusion sectionβββββ
Chapter 17: Sustainable AI: The conclusion was updated, figure captions and references were fixed, and section headers were added for cross-referencingβββββ
Chapter 9: Efficient AI: Section headers were added for easier cross-referencing, figure captions and references were corrected, and captions were added to all tablesβββββ
Chapter 6: Data Engineering: The chapter now includes additional slides and updated exercises, along with a fix to enable PDF builds by converting the colab-badge.svg to PNGβββββ
Chapter 8: AI Training: Added short captions to all videos, included section headers for easier cross-referencing, and corrected figure captions and referencesβββββ
Chapter 7: AI Frameworks: Fixed broken slide links, added section headers for easier cross-referencing, and corrected figure captions and referencesβββββ
Chapter 13: ML Operations: Added short captions to videos, renamed the βembedded opsβ section to just βopsβ, and corrected the bib file extensionβββββ
Chapter 15: Security & Privacy: This update includes captions for all tables and video content, along with a change in the colab-badge.svg file format to enable PDF buildsβββββ
Chapter 5: AI Workflow: Slide links were fixed, section headers were added to facilitate cross-referencing, and an error in the bib file header was correctedβββββ
Chapter 19: AI for Good: Section headers were added for easier cross-referencing, short captions were added to the videos, and the SVG image was changed to PNG to enable PDF buildsβββββ
Chapter 12: Benchmarking AI: The chapter content was cleaned up, including slides, exercises, and labs, section headers were added to enable cross-referencing, and punctuation inconsistencies were correctedβββββ
Chapter 11: AI Acceleration: Added section headers for easier cross-referencing, fixed broken links, and updated figure captions and referencesβββββ
Chapter 2: ML Systems: Added section headers for easier cross-referencing, updated names throughout the chapter, and removed the βEmbedded Systemsβ section to focus solely on ML systemsβββββ
Chapter 16: Responsible AI: Section headers were added for easier cross-referencing, a broken link was fixed, and grammar errors were correctedβββββ
Generative Ai: Section headers were added for easier cross-referencing and βComing soonβ was changed to βComing soonββββββ
Chapter 1: Introduction: Section headers were added for easier cross-referencing, a bib file header error was corrected, and a cover image was added to the introduction chapterβββββ
Embedded Ml: Chapters 1 through 4 were edited and the collapse setting for the Embedded Ml chapter was set to falseβββββ
Embedded Sys: Chapters 1 through 4 were edited, additional slides were included, and the collapse setting was changedβββββ
Acknowledgements: Image logos were added and an initial draft of the acknowledgements chapter was createdβββββ
Dsp Spectral Features Block: The text now uses consistent punctuation and corrects instances of βsβ to βsββββββ
Lab: Arduino Image Classification: Punctuation has been corrected throughout the labβββββ
Kws Feature Eng: Punctuation has been corrected throughout the chapterβββββ
Motion Classify Ad: Corrected punctuation throughout the chapterβββββ
Niclav Sys: Punctuation has been corrected throughout the chapter
π Mar 21 at 11:55 AM
π Chapters
βββββ
Chapter 6: Data Engineering: The Resources section now includes introductory text for each part and can be collapsed, exercise callouts have been added, and slides have been moved to the end of the pageβββββ
Embedded Sys: The Resources section now includes introductory text for each part and can be collapsed, additional slides were added, and all slides have been moved to the end of the pageβββββ
Chapter 19: AI for Good: The Resources section now includes introductory text for each part and can be collapsed, while slides have been moved to the end of the pageβββββ
Chapter 12: Benchmarking AI: The βResourcesβ section was added to the end of all QMD files and includes introductory text for each part, which can now be collapsed. Slides were also moved to the end of the pageβββββ
Chapter 3: DL Primer: Resource sections now have introductory text and collapsible functionality, additional slides were included, and all slides are now located at the end of the pageβββββ
Chapter 9: Efficient AI: The Resources section now includes introductory text for each part and can be collapsed, additional slides were added, and an empty βResourcesβ section with headers was added to the end of all QMD filesβββββ
Embedded Ml: The Embedded Ml chapter now includes additional slides placed at the end of each page, along with an updated Resources section featuring introductory text for each part and collapsible functionalityβββββ
Chapter 7: AI Frameworks: The Resources section now includes introductory text for each part, collapsible functionality, and Colab badges. Slides have been moved to the end of the pageβββββ
Chapter 11: AI Acceleration: The Resources section in each QMD now includes introductory text and can be collapsed, and an empty βResourcesβ section has been added to the end of all QMD filesβββββ
Chapter 14: On-Device Learning: The Resources section now includes introductory text for each part and can be collapsed, additional slides were added, and all slides are now located at the end of the pageβββββ
Chapter 13: ML Operations: The Resources section now includes introductory text for each part and can be collapsed, additional slides were added, and all slides have been moved to the end of the pageβββββ
Chapter 10: Model Optimizations: A βResourcesβ section with collapsible introductory text was added to the end of all QMD files and slides were moved to the end of each pageβββββ
Chapter 15: Security & Privacy: The Resources section now has introductory text for each part and can be collapsed, additional slides were added, and slides were moved to the end of the pageβββββ
Chapter 16: Responsible AI: A Resources section with collapsible parts was added to the end of the chapter and slides were moved to the end of the pageβββββ
Chapter 17: Sustainable AI: Each resource section now has introductory text, slides are located at the end of pages, and an empty βResourcesβ section was added to all QMD filesβββββ
Chapter 8: AI Training: The Resources sections now have introductory text and can be collapsed, additional slides were added, and all slides are now located at the end of the pageβββββ
Chapter 5: AI Workflow: The Resources section now includes introductory text for each part and can be collapsed, while slides have been moved to the end of the page
π Mar 12 at 04:39 PM
π Chapters
βββββ
Chapter 10: Model Optimizations: Implemented non-ASCII character checking scripts and fixed style issues to ensure successful rendering. Six new chapters were also addedβββββ
Chapter 7: AI Frameworks: Added Colab notebooks for the chapter, included additional slides, fixed previous notes, and implemented scripts to check for non-ASCII charactersβββββ
Chapter 6: Data Engineering: The data engineering chapter now includes Colab notebooks, a new web scraping exercise in both the subsection and as a separate part of the exercises, and additional slidesβββββ
Chapter 11: AI Acceleration: The chapter content now excludes a figure reference and a Mermaid section, and the non-ASCII checker scripts have been correctedβββββ
Niclav Sys: Links were corrected and new scripts were added to check for and fix issues with non-ASCII charactersβββββ
Embedded Ml: Debug code was removed, arrow functionality was added to the style file, and custom callouts were implementedβββββ
Chapter 19: AI for Good: The chapter now includes additional slides, non-ASCII checking scripts, and various bug fixesβββββ
Chapter 12: Benchmarking AI: The chapter now includes additional slides, corrections to previous notes, and scripts for checking non-ASCII charactersβββββ
Chapter 3: DL Primer: The chapter now includes additional slides and incorporates non-( ) ASCII checker scripts with accompanying fixesβββββ
Embedded Sys: The chapter now includes additional slides and incorporates non-ASCII checking scripts with necessary fixesβββββ
Chapter 14: On-Device Learning: The chapter content was expanded with additional slides and (Non-) ASCII checker scripts were added along with necessary fixesβββββ
Chapter 13: ML Operations: The chapter now includes additional slides, corrected previous notes, and incorporates new scripts for checking non-ASCII charactersβββββ
Chapter 15: Security & Privacy: The chapter now includes additional slides and corrections to previous notesβββββ
Chapter 16: Responsible AI: The Responsible AI chapter now includes additional slides and has been styled for better renderingβββββ
Chapter 17: Sustainable AI: The chapter now includes additional slides and incorporates non-ASCII checking scripts with necessary fixesβββββ
Chapter 8: AI Training: The chapter now includes additional slides, non-( ) ASCII checker scripts were added, and style was fixed for successful renderingβββββ
Chapter 5: AI Workflow: The chapter now includes additional slides, corrected previous notes, and incorporates non-( ) ASCII checker scripts with relevant fixesβββββ
Chapter 9: Efficient AI: Incorporated non-ASCII checker scripts and resolved issues with non-ASCII characters in code examples
π Feb 03 at 09:53 AM
π Chapters
βββββ
Chapter 12: Benchmarking AI: Unpopulated list items were removed and the styling of list items was made more consistentβββββ
Chapter 13: ML Operations: The MCU example for smartwatches was updated and a reference was addedβββββ
Chapter 15: Security & Privacy: Video rendering is fixed, GDPR and CCPA section hyperlinks are improved, and the CCPA summary is more clearβββββ
Chapter 11: AI Acceleration: Video rendering in the chapter has been fixedβββββ
Chapter 19: AI for Good: Video rendering and YouTube shortened URL resolution have been fixedβββββ
Chapter 14: On-Device Learning: The rendering of itemized lists has been fixedβββββ
Chapter 3: DL Primer: Video rendering issues in the chapter have been fixedβββββ
Chapter 17: Sustainable AI: List item spacing was made consistent and a reference to the OECD blueprint paper was added
π Feb 02 at 05:12 PM
π Chapters
βββββ
Chapter 19: AI for Good: Several image links were fixed, all bibtex references were updated automatically, and the β81-figure-references/part-2β branch was mergedβββββ
Chapter 11: AI Acceleration: Several image links were fixed, bibtex entries were corrected, and all bibtex references were updated automaticallyβββββ
Chapter 13: ML Operations: Several image links were repaired, all bibtex references were updated automatically, and a figure rendering problem was resolvedβββββ
Chapter 15: Security & Privacy: Several image references were fixed, grammar was corrected, and video URLs were adjusted to ensure proper renderingβββββ
Chapter 17: Sustainable AI: Several image links were fixed, all bibtex references were updated automatically, and a broken chapter link was repairedβββββ
Chapter 6: Data Engineering: Updated callout content, added a web scraping exercise using Colab, automatically updated all bibtex references, and converted PNG images to JPG formatβββββ
Chapter 16: Responsible AI: The way @ is used in citations was fixed and all BibTeX references were updated automaticallyβββββ
Chapter 12: Benchmarking AI: Reference rendering in the chapter is fixed and all BibTeX references have been updated automaticallyβββββ
Chapter 10: Model Optimizations: A missing reference for quantization-aware pruning was added, an incomplete sparsity matrix filter illustration was removed and moved to a later section, and all bibtex references were automatically updatedβββββ
Chapter 14: On-Device Learning: The chapterβs bullet list was updated for clarity, and a broken hyperlinked image was removedβββββ
Chapter 3: DL Primer: SVG images were removed from the chapter and replaced with PNGs to ensure proper rendering in PDF outputsβββββ
Embedded Sys: Bibtex references throughout the chapter were automatically updatedβββββ
Chapter 8: AI Training: Bibtex references throughout the chapter were automatically updatedβββββ
Embedded Ml: The image format in the Embedded ML chapter has been switched to PNG
π Jan 02 at 12:08 PM
π Chapters
βββββ
Niclav Sys: A typo was corrected in the Installing the OpenMV IDE sectionβββββ
Chapter 7: AI Frameworks: The chapter content now includes corrections to a callout-tip and minor syntax issues
π Dec 19 at 09:21 AM
π Chapters
βββββ
Chapter 10: Model Optimizations: The chapter now includes figures and formatting and reference errors have been corrected
π Dec 18 at 11:08 AM
π Chapters
βββββ
Chapter 12: Benchmarking AI: The chapterβs content was moved to the benchmarks/leaderboards section and a problem with reference separators was correctedβββββ
Chapter 17: Sustainable AI: Content related to sustainable AI was moved to the benchmarks/leaderboards section, wording about power draw was corrected, and a citation was fixedβββββ
Chapter 10: Model Optimizations: Resolved a markdown formatting issue that affected Windows users
π Dec 13 at 12:01 PM
π Chapters
βββββ
Chapter 7: AI Frameworks: The Colab notebooks for AI framework examples have been updated
π Dec 13 at 10:00 AM
π Chapters
βββββ
Chapter 9: Efficient AI: A broken URL link was fixed
π Dec 12 at 04:10 PM
π Chapters
βββββ
Chapter 12: Benchmarking AI: Reference spacing in the chapter has been fixed
π Dec 12 at 01:21 PM
π Chapters
βββββ
Chapter 8: AI Training: The file path for this chapter was updatedβββββ
Chapter 10: Model Optimizations: A missing reference for an attention paper was updated
π Dec 12 at 09:34 AM
π Chapters
βββββ
Chapter 10: Model Optimizations: References now use square brackets instead of other formatting
π Dec 11 at 04:37 PM
π Chapters
βββββ
Chapter 3: DL Primer: The DL primer no longer includes an activation function and its computation graph has been moved to the training sectionβββββ
Chapter 8: AI Training: The DL primer activation function was removed and the computation graph was moved to the training sectionβββββ
Chapter 12: Benchmarking AI: The chapterβs text was updated for improved clarity and accuracy, and several new examples were addedβββββ
Chapter 11: AI Acceleration: The chapterβs terminology has been updated for clarity and explanations of hardware acceleration concepts have been refinedβββββ
Chapter 14: On-Device Learning: Updated terminology for consistency and improved explanations of key conceptsβββββ
Generative Ai: Text in the chapter has been cleaned upβββββ
Chapter 18: Robust AI: Text in the chapter has been cleaned upβββββ
Chapter 6: Data Engineering: Several sentences were updated for improved clarity and concisenessβββββ
Embedded Ml: Various words were changed for clarity and accuracyβββββ
Embedded Sys: Several words were changed for clarity and precision
π Dec 11 at 02:06 PM
π Chapters
βββββ
Chapter 12: Benchmarking AI: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Chapter 6: Data Engineering: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Embedded Sys: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Chapter 7: AI Frameworks: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Chapter 11: AI Acceleration: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Lab: Arduino Image Classification: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Kws Nicla: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Chapter 10: Model Optimizations: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Chapter 16: Responsible AI: The text now consistently uses βTinyMLβ instead of βtinyMLββββββ
Chapter 5: AI Workflow: The text now consistently uses βTinyMLβ instead of βtinyMLβ
π Dec 11 at 01:50 PM
π Chapters
βββββ
Chapter 9: Efficient AI: References were added for mentioned datasets in the Efficient AI chapter, as well as for ResNet-SE and ResNeXt papers. Each chapter now has its own dedicated references fileβββββ
Chapter 7: AI Frameworks: The AI Frameworks chapter now has its own reference file and a fixed URLβββββ
Chapter 10: Model Optimizations: The chapter now uses consistent terminology (FP32), removed redundant information about the lottery ticket hypothesis, and each chapter has its own reference listβββββ
Chapter 11: AI Acceleration: The chapter now includes additional references for machine learning and reinforcement learning applications in architecture design space exploration, general-purpose computing, chip floorplanning, and logic synthesisβββββ
Chapter 19: AI for Good: The AI for Good chapter now has its own dedicated references fileβββββ
Chapter 12: Benchmarking AI: The references for Chapter 12 are now stored in a separate fileβββββ
Chapter 6: Data Engineering: References are now distributed to individual chapter filesβββββ
Chapter 3: DL Primer: Each chapter now has its own dedicated references fileβββββ
Dsp Spectral Features Block: Distributed references so each chapter has its own references fileβββββ
Embedded Ml: Distributed references to individual chaptersβββββ
Embedded Sys: Distributed references to individual chaptersβββββ
Generative Ai: The Generative AI chapter now has its own dedicated references fileβββββ
Lab: Arduino Image Classification: Each chapter now has its own dedicated references fileβββββ
Kws Feature Eng: Distributed references so each chapter has its own references fileβββββ
Kws Nicla: References are now chapter-specificβββββ
Motion Classify Ad: References are now chapter-specificβββββ
Niclav Sys: References are now chapter-specificβββββ
Object Detection Fomo: The Object Detection Fomo chapter now has its own dedicated references fileβββββ
Chapter 14: On-Device Learning: Each chapter now has its own reference file and the book was updated with changes from the upstream main branchβββββ
Chapter 13: ML Operations: References are now distributed to each chapterβs own filesβββββ
Chapter 15: Security & Privacy: Each chapter now has its own references file and the book was updated with changes from the upstream main branchβββββ
Chapter 16: Responsible AI: The Responsible AI chapter now has its own dedicated references fileβββββ
Chapter 18: Robust AI: The Robust AI chapter now has a dedicated references fileβββββ
Chapter 17: Sustainable AI: The references for each chapter are now stored in separate filesβββββ
Chapter 8: AI Training: Each chapter now has a dedicated references fileβββββ
Chapter 5: AI Workflow: The workflow chapter now has its own dedicated references file
π Dec 10 at 04:03 PM
π Chapters
βββββ
Chapter 8: AI Training: References are now formatted to appear before periods
π Dec 10 at 03:38 PM
π Chapters
βββββ
Chapter 12: Benchmarking AI: The images folder was reorganized with subfolders based on file type and all files were restructured into a new folder systemβββββ
Chapter 6: Data Engineering: The images folder has been reorganized with subfolders based on file type and all files have been restructured into a new folder systemβββββ
Dsp Spectral Features Block: The images directory has been reorganized with subfolders based on file type and all files have been restructured into a new folder systemβββββ
Embedded Ml: The image directory has been reorganized with subfolders by file type and all files have been restructured into a new folder systemβββββ
Generative Ai: The images directory was reorganized with subfolders by file type and all files were restructured into a new folder systemβββββ
Motion Classify Ad: The image directory was reorganized with subfolders based on file type and all files were restructured into a new folder systemβββββ
Niclav Sys: The image directory has been reorganized with subfolders based on file type and all files have been restructured into a new folder systemβββββ
Chapter 16: Responsible AI: The image directory was reorganized with subfolders based on file type and all files were restructured into a new folder systemβββββ
Chapter 19: AI for Good: The image folder was reorganized with subfolders based on filetype and all files were restructured into a new folder systemβββββ
Chapter 3: DL Primer: The image directory has been reorganized with subfolders based on file type and all files have been restructured into a new folder systemβββββ
Chapter 9: Efficient AI: The image folder was reorganized with subfolders by file type and all files were restructured into a new folder systemβββββ
Embedded Sys: The image folder now has subfolders based on file type and all files have been reorganized into a new folder structureβββββ
Chapter 7: AI Frameworks: The images folder was reorganized with subfolders based on file type, and all files were restructured into a more organized folder systemβββββ
Chapter 11: AI Acceleration: The images folder has been reorganized with subfolders based on file type and all files have been restructured into a more organized folder systemβββββ
Lab: Arduino Image Classification: The image classification lab now has subfolders within the images/ directory and its files are reorganized into a more structured formatβββββ
Kws Feature Eng: The images folder has been reorganized with subfolders based on file type and all files have been restructured into a new folder systemβββββ
Kws Nicla: The image directory was reorganized with subfolders based on file type and all files were restructured into a more organized folder systemβββββ
Object Detection Fomo: The image directory was reorganized with subfolders based on file type and all files were restructured into a more organized folder systemβββββ
Chapter 14: On-Device Learning: The image folder was reorganized with subfolders based on file type and all files were restructured into a new folder systemβββββ
Chapter 13: ML Operations: The image directory was reorganized with subfolders based on file type, and all files were restructured into a more organized folder systemβββββ
Chapter 10: Model Optimizations: The image directory was reorganized with subfolders based on file type and all files were restructured into a new folder systemβββββ
Chapter 15: Security & Privacy: The image folder was reorganized with subfolders based on file type and all files were reorganized into a new folder structureβββββ
Chapter 17: Sustainable AI: The image directory has been reorganized with subfolders by file type and all files have been restructured into a new folder systemβββββ
Chapter 8: AI Training: The images folder was restructured with subfolders based on file type and all files were reorganized into a new folder structureβββββ
Chapter 5: AI Workflow: The images directory was reorganized with subfolders based on file type, and all files were restructured into a more organized folder systemβββββ
Chapter 18: Robust AI: Files have been reorganized into a folder structure