{"product_id":"interpretable-machine-learning-with-python-second-edition-build-explainable-fair-and-robust-high-performance-models-with-hands-on-real-world-exa-9781803235424","title":"Interpretable Machine Learning with Python - Second Edition: Build explainable, fair, and robust high-performance models with hands-on, real-world exa","description":"\u003cp\u003e\u003cstrong\u003eA deep dive into the key aspects and challenges of machine learning interpretability using a comprehensive toolkit, including SHAP, feature importance, and causal inference, to build fairer, safer, and more reliable models.\u003c\/strong\u003e\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003ePurchase of the print or Kindle book includes a free eBook in PDF format.\u003c\/strong\u003e\u003c\/p\u003eKey Features\u003cul\u003e\n\u003cli\u003eInterpret real-world data, including cardiovascular disease data and the COMPAS recidivism scores\u003c\/li\u003e\n\u003cli\u003eBuild your interpretability toolkit with global, local, model-agnostic, and model-specific methods\u003c\/li\u003e\n\u003cli\u003eAnalyze and extract insights from complex models from CNNs to BERT to time series models\u003c\/li\u003e\n\u003c\/ul\u003eBook Description\u003cp\u003eInterpretable 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.\u003c\/p\u003e\u003cp\u003eBuild 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.\u003c\/p\u003e\u003cp\u003eIn 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.\u003c\/p\u003e\u003cp\u003eBy 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.\u003c\/p\u003eWhat you will learn\u003cul\u003e\n\u003cli\u003eProgress from basic to advanced techniques, such as causal inference and quantifying uncertainty\u003c\/li\u003e\n\u003cli\u003eBuild your skillset from analyzing linear and logistic models to complex ones, such as CatBoost, CNNs, and NLP transformers\u003c\/li\u003e\n\u003cli\u003eUse monotonic and interaction constraints to make fairer and safer models\u003c\/li\u003e\n\u003cli\u003eUnderstand how to mitigate the influence of bias in datasets\u003c\/li\u003e\n\u003cli\u003eLeverage sensitivity analysis factor prioritization and factor fixing for any model\u003c\/li\u003e\n\u003cli\u003eDiscover how to make models more reliable with adversarial robustness\u003c\/li\u003e\n\u003c\/ul\u003eWho this book is for\u003cp\u003eThis book is for data scientists, machine learning developers, machine learning engineers, MLOps engineers, and data stewards who have an increasingly critical responsibility to explain how the artificial intelligence systems they develop work, their impact on decision making, and how they identify and manage bias. It's also a useful resource for self-taught ML enthusiasts and beginners who want to go deeper into the subject matter, though a good grasp of the Python programming language is needed to implement the examples.\u003c\/p\u003eTable of Contents\u003col\u003e\n\u003cli\u003eInterpretation, Interpretability and Explainability; and why does it all matter?\u003c\/li\u003e\n\u003cli\u003eKey Concepts of Interpretability\u003c\/li\u003e\n\u003cli\u003eInterpretation Challenges\u003c\/li\u003e\n\u003cli\u003eGlobal Model-agnostic Interpretation Methods\u003c\/li\u003e\n\u003cli\u003eLocal Model-agnostic Interpretation Methods\u003c\/li\u003e\n\u003cli\u003eAnchors and Counterfactual Explanations\u003c\/li\u003e\n\u003cli\u003eVisualizing Convolutional Neural Networks\u003c\/li\u003e\n\u003cli\u003eInterpreting NLP Transformers\u003c\/li\u003e\n\u003cli\u003eInterpretation Methods for Multivariate Forecasting and Sensitivity Analysis\u003c\/li\u003e\n\u003cli\u003eFeature Selection and Engineering for Interpretability\u003c\/li\u003e\n\u003cli\u003eBias Mitigation and Causal Inference Methods\u003c\/li\u003e\n\u003cli\u003eMonotonic Constraints and Model Tuning for Interpretability\u003c\/li\u003e\n\u003cli\u003eAdversarial Robustness\u003c\/li\u003e\n\u003cli\u003eWhat's Next for Machine Learning Interpretability?\u003c\/li\u003e\n\u003c\/ol\u003e\u003cbr\u003e","brand":"Packt Publishing","offers":[{"title":"Default Title","offer_id":50692316561682,"sku":"9781803235424","price":45.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0831\/4771\/8930\/files\/img_c5aa6975-4832-4268-90cf-40444ee8a557.jpg?v=1734121228","url":"https:\/\/surprise-castle.myshopify.com\/products\/interpretable-machine-learning-with-python-second-edition-build-explainable-fair-and-robust-high-performance-models-with-hands-on-real-world-exa-9781803235424","provider":"Surprise Castle","version":"1.0","type":"link"}