Interpretable AI, Video Edition

Video description

In Video Editions the narrator reads the book while the content, figures, code listings, diagrams, and text appear on the screen. Like an audiobook that you can also watch as a video.

AI doesn’t have to be a black box. These practical techniques help shine a light on your model’s mysterious inner workings. Make your AI more transparent, and you’ll improve trust in your results, combat data leakage and bias, and ensure compliance with legal requirements.

In Interpretable AI, you will learn:

  • Why AI models are hard to interpret
  • Interpreting white box models such as linear regression, decision trees, and generalized additive models
  • Partial dependence plots, LIME, SHAP and Anchors, and other techniques such as saliency mapping, network dissection, and representational learning
  • What fairness is and how to mitigate bias in AI systems
  • Implement robust AI systems that are GDPR-compliant

Interpretable AI opens up the black box of your AI models. It teaches cutting-edge techniques and best practices that can make even complex AI systems interpretable. Each method is easy to implement with just Python and open source libraries. You’ll learn to identify when you can utilize models that are inherently transparent, and how to mitigate opacity when your problem demands the power of a hard-to-interpret deep learning model.

About the Technology
It’s often difficult to explain how deep learning models work, even for the data scientists who create them. Improving transparency and interpretability in machine learning models minimizes errors, reduces unintended bias, and increases trust in the outcomes. This unique book contains techniques for looking inside “black box” models, designing accountable algorithms, and understanding the factors that cause skewed results.

About the Book
Interpretable AI teaches you to identify the patterns your model has learned and why it produces its results. As you read, you’ll pick up algorithm-specific approaches, like interpreting regression and generalized additive models, along with tips to improve performance during training. You’ll also explore methods for interpreting complex deep learning models where some processes are not easily observable. AI transparency is a fast-moving field, and this book simplifies cutting-edge research into practical methods you can implement with Python.

What's Inside
  • Techniques for interpreting AI models
  • Counteract errors from bias, data leakage, and concept drift
  • Measuring fairness and mitigating bias
  • Building GDPR-compliant AI systems

About the Reader
For data scientists and engineers familiar with Python and machine learning.

About the Author
Ajay Thampi is a machine learning engineer focused on responsible AI and fairness.

A sound introduction for practitioners to the exciting field of interpretable AI.
- Pablo Roccatagliata, Torcuato Di Tella University

Ajay Thampi explains in an easy-to-understand way the importance of interpretability in machine learning.
- Ariel Gamiño, Athenahealth

Effectively demystifies interpretable AI for novice and pro alike.
- Vijayant Singh, Razorpay

Concrete examples help the understanding and building of interpretable AI systems.
- Izhar Haq, Long Island University

Table of contents

  1. Part 1. Interpretability basics
  2. Chapter 1. Introduction
  3. Chapter 1. Types of machine learning systems
  4. Chapter 1. Building Diagnostics+ AI
  5. Chapter 1. Gaps in Diagnostics+ AI
  6. Chapter 1. Building a robust Diagnostics+ AI system
  7. Chapter 1. Interpretability vs. explainability
  8. Chapter 1. What will I learn in this book?
  9. Chapter 1. Summary
  10. Chapter 2. White-box models
  11. Chapter 2. Diagnostics+—diabetes progression
  12. Chapter 2. Linear regression
  13. Chapter 2. Decision trees
  14. Chapter 2. Generalized additive models (GAMs)
  15. Chapter 2. Looking ahead to black-box models
  16. Chapter 2. Summary
  17. Part 2. Interpreting model processing
  18. Chapter 3. Model-agnostic methods: Global interpretability
  19. Chapter 3. Tree ensembles
  20. Chapter 3. Interpreting a random forest
  21. Chapter 3. Model-agnostic methods: Global interpretability
  22. Chapter 3. Summary
  23. Chapter 4. Model-agnostic methods: Local interpretability
  24. Chapter 4. Exploratory data analysis
  25. Chapter 4. Deep neural networks
  26. Chapter 4. Interpreting DNNs
  27. Chapter 4. LIME
  28. Chapter 4. SHAP
  29. Chapter 4. Anchors
  30. Chapter 4. Summary
  31. Chapter 5. Saliency mapping
  32. Chapter 5. Exploratory data analysis
  33. Chapter 5. Convolutional neural networks
  34. Chapter 5. Interpreting CNNs
  35. Chapter 5. Vanilla backpropagation
  36. Chapter 5. Guided backpropagation
  37. Chapter 5. Other gradient-based methods
  38. Chapter 5. Grad-CAM and guided Grad-CAM
  39. Chapter 5. Which attribution method should I use?
  40. Chapter 5. Summary
  41. Part 3. Interpreting model representations
  42. Chapter 6. Understanding layers and units
  43. Chapter 6. Convolutional neural networks: A recap
  44. Chapter 6. Network dissection framework
  45. Chapter 6. Interpreting layers and units
  46. Chapter 6. Summary
  47. Chapter 7. Understanding semantic similarity
  48. Chapter 7. Exploratory data analysis
  49. Chapter 7. Neural word embeddings
  50. Chapter 7. Interpreting semantic similarity
  51. Chapter 7. Summary
  52. Part 4. Fairness and bias
  53. Chapter 8. Fairness and mitigating bias
  54. Chapter 8. Fairness notions
  55. Chapter 8. Interpretability and fairness
  56. Chapter 8. Mitigating bias
  57. Chapter 8. Datasheets for datasets
  58. Chapter 8. Summary
  59. Chapter 9. Path to explainable AI
  60. Chapter 9. Counterfactual explanations
  61. Chapter 9. Summary
  62. Appendix A. Getting set up
  63. Appendix A. Git code repository
  64. Appendix A. Conda environment
  65. Appendix A. Jupyter notebooks
  66. Appendix A. Docker
  67. Appendix B. PyTorch
  68. Appendix B. Installing PyTorch
  69. Appendix B. Tensors
  70. Appendix B. Dataset and DataLoader
  71. Appendix B. Modeling

Product information

  • Title: Interpretable AI, Video Edition
  • Author(s): Ajay Thampi
  • Release date: July 2022
  • Publisher(s): Manning Publications
  • ISBN: None