Interpretable Machine Learning with Python. Build explainable, fair, and robust high-performance models with hands-on, real-world examples - Second Ed

Interpretable Machine Learning with Python. Build explainable, fair, and robust high-performance models with hands-on, real-world examples - Second Ed - Opis

Interpretable Machine Learning with Python, Second Edition, brings to light the key concepts of interpreting machine learning models by analyzing real-world data, providing you with a wide range of skills and tools to decipher the results of even the most complex models.Build your interpretability toolkit with several use cases, from flight delay prediction to waste classification to COMPAS risk assessment scores. This book is full of useful techniques, introducing them to the right use case. Learn traditional methods, such as feature importance and partial dependence plots to integrated gradients for NLP interpretations and gradient-based attribution methods, such as saliency maps.In addition to the step-by-step code, you’ll get hands-on with tuning models and training data for interpretability by reducing complexity, mitigating bias, placing guardrails, and enhancing reliability.By the end of the book, you’ll be confident in tackling interpretability challenges with black-box models using tabular, language, image, and time series data. Spis treści: 1. Interpretation, Interpretability and Explainability; and why does it all matter?2. Key Concepts of Interpretability3. Interpretation Challenges4. Global Model-agnostic Interpretation Methods5. Local Model-agnostic Interpretation Methods6. Anchors and Counterfactual Explanations7. Visualizing Convolutional Neural Networks8. Interpreting NLP Transformers9. Interpretation Methods for Multivariate Forecasting and Sensitivity Analysis10. Feature Selection and Engineering for Interpretability11. Bias Mitigation and Causal (...) więcej Inference Methods12. Monotonic Constraints and Model Tuning for Interpretability13. Adversarial Robustness14. What's Next for Machine Learning Interpretability? mniej