Responsible AI in Practice: A Practical Guide to Safe and Human AI
暫譯: 實踐中的負責任人工智慧：安全與人性化人工智慧的實用指南
Duke, Toju, Giudici, Paolo
相關主題
商品描述
This book is the first practical book on AI risk assessment and management. It will enable you to evaluate and implement safe and accurate AI models and applications. The book features risk assessment frameworks, statistical metrics and code, a risk taxonomy curated from real-world case studies, and insights into AI regulation and policy, and is an essential tool for AI governance teams, AI auditors, AI ethicists, machine learning (ML) practitioners, Responsible AI practitioners, and computer science and data science students building safe and trustworthy AI systems across businesses, organizations, and universities.
The centerpiece of this book is a risk management and assessment framework titled "Safe Human-centered AI (SAFE-HAI)," which highlights AI risks across the following Responsible AI principles: accuracy, sustainability and robustness, explainability, transparency and accountability, fairness, privacy and human rights, human-centered AI, and AI governance. Using several statistical metrics such as Area Under Curve (AUC), Rank Graduation Accuracy, and Shapley values, you will learn to apply Lorenz curves to measure risk and inequality across the different principles and will be equipped with a taxonomy/scoring rubric to identify and mitigate identified risks.
This book is a true practical guide and covers a real-world case study using the proposed SAFE-HAI framework. The book will help you adopt standards and voluntary codes of conduct in compliance with AI risk and safety policies and regulations, including those from the NIST (National Institute of Standards and Technology) and EU AI Act (European Commission).
What You Will Learn
- Know the key principles behind Responsible AI and associated risks
- Become familiar with risk assessment frameworks, statistical metrics, and mitigation measures for identified risks
- Be aware of the fundamentals of AI regulations and policies and how to adopt them
- Understand AI governance basics and implementation guidelines
Who This Book Is For
AI governance teams, AI auditors, AI ethicists, machine learning (ML) practitioners, Responsible AI practitioners, and computer science and data science students building safe and trustworthy AI systems across businesses, organizations, and universities
商品描述(中文翻譯)
這本書是關於人工智慧（AI）風險評估與管理的第一本實用書籍。它將使您能夠評估和實施安全且準確的AI模型和應用。書中包含風險評估框架、統計指標和程式碼，從真實案例研究中整理出的風險分類法，以及對AI法規和政策的見解，是AI治理團隊、AI審計師、AI倫理學家、機器學習（ML）從業者、負責任的AI從業者，以及在企業、組織和大學中構建安全可靠的AI系統的計算機科學和數據科學學生的必備工具。
本書的核心是一個名為「安全以人為中心的AI（Safe Human-centered AI，SAFE-HAI）」的風險管理和評估框架，強調在以下負責任的AI原則下的AI風險：準確性、可持續性和穩健性、可解釋性、透明性和問責性、公平性、隱私和人權、以人為中心的AI，以及AI治理。通過使用多個統計指標，如曲線下面積（Area Under Curve，AUC）、排名畢業準確度（Rank Graduation Accuracy）和Shapley值，您將學會應用Lorenz曲線來衡量不同原則之間的風險和不平等，並將獲得一個分類法/評分標準，以識別和減輕已識別的風險。
這本書是真正的實用指南，涵蓋了使用所提議的SAFE-HAI框架的真實案例研究。這本書將幫助您採用符合AI風險和安全政策及法規的標準和自願行為準則，包括來自NIST（國家標準與技術研究所）和歐盟AI法案（European Commission）的規範。
您將學到的內容：
- 知曉負責任的AI背後的關鍵原則及相關風險
- 熟悉風險評估框架、統計指標和已識別風險的減輕措施
- 了解AI法規和政策的基本原則及如何採用它們
- 理解AI治理的基本概念和實施指導方針
本書適合對象：
AI治理團隊、AI審計師、AI倫理學家、機器學習（ML）從業者、負責任的AI從業者，以及在企業、組織和大學中構建安全可靠的AI系統的計算機科學和數據科學學生。
作者簡介
Toju Duke has more than 18 years of experience spanning across advertising, retail, not-for profit, and tech, She is a popular speaker, author, thought leader, and advisor on Responsible AI. Toju worked at Google for 10 years where she spent the last three years as Program Manager on Responsible AI, leading various Responsible AI programs across Google's product and research teams, and with a primary focus on large-scale models and Responsible AI processes. She is also the founder of Diverse AI, a community interest organization with a mission to support and champion under-represented groups to build a diverse and inclusive AI future. In 2023, she published Building Responsible AI Algorithms: A Framework for Transparency, Fairness, Safety, Privacy, and Robustness (Apress). She provides consultation and advice on Responsible AI practices worldwide.
作者簡介(中文翻譯)
Toju Duke 擁有超過 18 年的經驗，涵蓋廣告、零售、非營利組織和科技領域。她是一位受歡迎的演講者、作者、思想領袖和負責任人工智慧（Responsible AI）的顧問。Toju 在 Google 工作了 10 年，其中最後三年擔任負責任人工智慧的計畫經理，領導 Google 產品和研究團隊的各項負責任人工智慧計畫，主要專注於大規模模型和負責任人工智慧流程。她也是 Diverse AI 的創辦人，這是一個社區利益組織，旨在支持和倡導代表性不足的群體，建立多元和包容的人工智慧未來。2023 年，她出版了《Building Responsible AI Algorithms: A Framework for Transparency, Fairness, Safety, Privacy, and Robustness》（Apress）。她在全球提供有關負責任人工智慧實踐的諮詢和建議。
