What this book covers
Chapter 1, Beyond Code Debugging, covers a brief review of code debugging and why debugging machine learning models goes beyond that.
Chapter 2, Machine Learning Life Cycle, teaches you how to design a modular machine learning life cycle for your projects.
Chapter 3, Debugging toward Responsible AI, explains concerns, challenges, and some of the techniques in responsible machine learning modeling.
Chapter 4, Detecting Performance and Efficiency Issues in Machine Learning Models, teaches you how to correctly assess the performance of your machine learning models.
Chapter 5, Improving the Performance of Machine Learning Models, teaches you different techniques to improve the performance and generalizability of your machine learning models.
Chapter 6, Interpretability and Explainability in Machine Learning Modeling, covers some machine learning explainability techniques.
Chapter 7, Decreasing Bias and Achieving Fairness, explains some technical details and tools that you can use to assess fairness and reduce biases in your models.
Chapter 8, Controlling Risks Using Test-Driven Development, shows how to reduce the risk of unreliable modeling using test-driven development tools and techniques.
Chapter 9, Testing and Debugging for Production, explains testing and model monitoring techniques to have reliable models in production.
Chapter 10, Versioning and Reproducible Machine Learning Modeling, teaches you how to use data and model versioning to achieve reproducibility in your machine learning projects.
Chapter 11, Avoiding and Detecting Data and Concept Drifts, teaches you how to detect drifts in your machine learning models to have reliable models in production.
Chapter 12, Going Beyond ML Debugging with Deep Learning, covers an introduction to deep learning modeling.
Chapter 13, Advanced Deep Learning Techniques, covers convolutional neural networks, transformers, and graph neural networks for deep learning modeling of different data types.
Chapter 14, Introduction to Recent Advancements in Machine Learning, explains an introduction to recent advancements in generative modeling, reinforcement learning, and self-supervised learning.
Chapter 15, Correlation versus Causality, explains the benefits of, and some practical techniques for, causal modeling.
Chapter 16, Security and Privacy in Machine Learning, shows some of the challenges in preserving privacy and ensuring security in machine learning settings, and teaches you a few techniques to tackle those challenges.
Chapter 17, Human-in-the-Loop Machine Learning, explains the benefits and challenges of human-in-the-loop modeling.
