Machine learning for high-risk applications : approaches to responsible AI
Material type: TextPublication details: Beijng : O'Reilly, ©2023Description: xxi, 438 p. : ill. ; 24 cmISBN:- 9789355429728
- 006.31 HAL-M
Item type | Current library | Collection | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|---|
Books | IIITD General Stacks | Computer Science and Engineering | 006.31 HAL-M (Browse shelf(Opens below)) | Available | 012940 |
Browsing IIITD shelves, Shelving location: General Stacks, Collection: Computer Science and Engineering Close shelf browser (Hides shelf browser)
006.31 GOO-D Deep learning | 006.31 GOP-D Deep learning : core concepts, methods and applications | 006.31 GRA-K Kubeflow for machine learning : | 006.31 HAL-M Machine learning for high-risk applications : approaches to responsible AI | 006.31 HOP-L Learning tensorflow : | 006.31 HOS-H A human's guide to machine intelligence : | 006.31 KEL-D Deep learning |
Includes bibliographical references and index.
Part 1. Theories and practical applications of AI risk management. Contemporary machine learning risk management -- Interpretable and explainable machine learning -- Debugging machine learning systems for safety and performance -- Managing bias in machine learning -- Security for machine learning -- Part 2. Putting AI risk management into action. Explainable boosting machines and explaining XGBoost -- Explaining a PyTorch image classifier -- Selecting and debugging XGBoost models -- Debuggins a PyTorch image classifier -- Testing and remediating bias with XGBoost -- Red-teaming XGBoost -- Part 3. Conclusion. How to succeed in high-risk machine learning.
The past decade has witnessed the broad adoption of artificial intelligence and machine learning (AI/ML) technologies. However, a lack of oversight in their widespread implementation has resulted in some incidents and harmful outcomes that could have been avoided with proper risk management. Before we can realize AI/ML's true benefit, practitioners must understand how to mitigate its risks. This book describes approaches to responsible AI--a holistic framework for improving AI/ML technology, business processes, and cultural competencies that builds on best practices in risk management, cybersecurity, data privacy, and applied social science. Authors Patrick Hall, James Curtis, and Parul Pandey created this guide for data scientists who want to improve real-world AI/ML system outcomes for organizations, consumers, and the public.
There are no comments on this title.