{"product_id":"9781617297649","title":"Interpretable AI : Building explainable machine learning systems","description":"\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd style=\"\"\u003e\u003cstrong\u003eAuthor\/Contributor(s):\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd style=\"\"\u003eThampi, Ajay\u003cbr\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"\"\u003e\u003cstrong\u003ePublisher:\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003eManning\u003cbr\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"\"\u003e\u003cstrong\u003eDate:\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd\u003e7\/5\/2022\u003cbr\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"\"\u003e\u003cstrong\u003eBinding:\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd style=\"\"\u003ePaperback\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"\"\u003e\u003cstrong\u003eCondition:\u003c\/strong\u003e\u003c\/td\u003e\n\u003ctd style=\"\"\u003eNEW\u003cbr\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\u003cb\u003eAI 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.\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003eIn \u003ci\u003eInterpretable AI\u003c\/i\u003e, you will learn:\u003cbr\u003e\u003cbr\u003eWhy AI models are hard to interpret\u003cbr\u003eInterpreting white box models such as linear regression, decision trees, and generalized additive models\u003cbr\u003ePartial dependence plots, LIME, SHAP and Anchors, and other techniques such as saliency mapping, network dissection, and representational learning\u003cbr\u003eWhat fairness is and how to mitigate bias in AI systems\u003cbr\u003eImplement robust AI systems that are GDPR-compliant\u003cbr\u003e\u003cbr\u003e\u003ci\u003eInterpretable AI\u003c\/i\u003e 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.\u003cbr\u003e\u003cbr\u003e\u003cb\u003eAbout the technology\u003c\/b\u003e\u003cbr\u003eIt’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.\u003cbr\u003e\u003cbr\u003e\u003cb\u003eAbout the book\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eInterpretable AI\u003c\/i\u003e 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.\u003cbr\u003e\u003cbr\u003eWhat's inside\u003cbr\u003e\u003cbr\u003eTechniques for interpreting AI models\u003cbr\u003eCounteract errors from bias, data leakage, and concept drift\u003cbr\u003eMeasuring fairness and mitigating bias\u003cbr\u003eBuilding GDPR-compliant AI systems\u003cbr\u003e\u003cbr\u003e\u003cb\u003eAbout the reader\u003c\/b\u003e\u003cbr\u003eFor data scientists and engineers familiar with Python and machine learning.\u003cbr\u003e\u003cb\u003eAbout the author\u003c\/b\u003e\u003cbr\u003e\u003cb\u003eAjay Thampi\u003c\/b\u003e is a machine learning engineer focused on responsible AI and fairness.\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003ePART 1 INTERPRETABILITY BASICS\u003cbr\u003e1 Introduction\u003cbr\u003e2 White-box models\u003cbr\u003ePART 2 INTERPRETING MODEL PROCESSING\u003cbr\u003e3 Model-agnostic methods: Global interpretability\u003cbr\u003e4 Model-agnostic methods: Local interpretability\u003cbr\u003e5 Saliency mapping\u003cbr\u003ePART 3 INTERPRETING MODEL REPRESENTATIONS\u003cbr\u003e6 Understanding layers and units\u003cbr\u003e7 Understanding semantic similarity\u003cbr\u003ePART 4 FAIRNESS AND BIAS\u003cbr\u003e8 Fairness and mitigating bias\u003cbr\u003e9 Path to explainable AI","brand":"Manning","offers":[{"title":"Default Title","offer_id":48176681222399,"sku":"9781617297649","price":59.99,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0452\/0886\/2873\/files\/Jacket_16320c9a-ca3c-4780-9adc-4636d5a9b9fb.jpg?v=1771351317","url":"https:\/\/massivebookshop.com\/products\/9781617297649","provider":"MASSIVE BOOKSHOP","version":"1.0","type":"link"}