{"product_id":"practicing-trustworthy-machine-learning-consistent-transparent-and-fair-ai-pipelines-9781098120276","title":"Practicing Trustworthy Machine Learning: Consistent, Transparent, and Fair AI Pipelines","description":"\u003cp\u003e\u003c\/p\u003e\u003cblockquote\u003e\n\u003cbr\u003eTo build industry-grade trusted ML systems, organizations must follow best practices for curating datasets and building models, such as explaining ML models and addressing fairness concerns and privacy leaks. This guide provides a practical starting point for development teams to produce secure, robust, less biased, and more explainable ML applications. \u003c\/blockquote\u003e\u003cp\u003e\u003cstrong\u003eFormat\u003c\/strong\u003e: Paperback \/ softback\u003cbr\u003e\u003cstrong\u003eLength\u003c\/strong\u003e: 350 pages\u003cbr\u003e\u003cstrong\u003ePublication date\u003c\/strong\u003e: 13 January 2023\u003cbr\u003e\u003cstrong\u003ePublisher\u003c\/strong\u003e: O'Reilly Media\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e\u003cbr\u003eThe increasing integration of artificial intelligence (AI) into critical domains such as medicine, law, and defense has led to significant investments by organizations in developing trustworthy machine learning (ML) models. Numerous books delve into theoretical concepts and frameworks, offering in-depth insights into the field. However, a practical guide that assists development teams in creating secure, robust, less biased, and more explainable ML systems is lacking.\u003cbr\u003e\u003cbr\u003eTo address this gap, authors Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar have compiled a comprehensive handbook titled \"Building Industry-Grade Trusted ML Systems.\" This book translates the best practices from the academic literature into a practical blueprint for building industry-grade trusted ML systems.\u003cbr\u003e\u003cbr\u003eIn the book, readers will gain valuable insights into methods for explaining ML models and their outputs to stakeholders, recognizing and addressing fairness concerns and privacy leaks in an ML pipeline, developing ML systems that are resilient against malicious attacks, and considering important systemic considerations such as trust debt management and the need for human intervention in certain ML obstacles.\u003cbr\u003e\u003cbr\u003eBy leveraging the expertise of these authors, engineers and data scientists will gain a solid foundation for deploying trustworthy ML applications in a noisy, messy, and often hostile world. The book serves as a valuable resource for anyone seeking to develop ML systems that prioritize security, robustness, fairness, and transparency.\u003c\/p\u003e\u003cp\u003e\u003cbr\u003e\u003cstrong\u003eDimension\u003c\/strong\u003e: 232 x 178 (mm)\u003cbr\u003e\u003cstrong\u003eISBN-13\u003c\/strong\u003e: 9781098120276\u003c\/p\u003e","brand":"Yada Pruksachatkun,Matthew McAteer,Subhabrata Majumdar","offers":[{"title":"Paperback \/ softback","offer_id":44100318920954,"sku":"9781098120276","price":46.84,"currency_code":"GBP","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0522\/4297\/2845\/products\/1674824187888_book.jpg?v=1675332185","url":"https:\/\/shulphink.com\/products\/practicing-trustworthy-machine-learning-consistent-transparent-and-fair-ai-pipelines-9781098120276","provider":"Shulph Ink","version":"1.0","type":"link"}