Interperetable AI: Building Explainable Machine Leaing Systems

by: Ajay Thampi (Author)

Publisher: Manning Publications
Edition: 1st

Publication Date: 17 Oct. 2022

Language: English

Print Length: 275 pages

ISBN-10: 161729764X

ISBN-13: 9781617297649

Book Description

AI models can become so complex that even experts have difficulty understanding them―and forget about explaining the nuances of a cluster of novel algorithms to a business stakeholder! InterpretableAI is filled with cutting-edge techniques that will improve your understanding of how your AI models function. InterpretableAI is a hands-on guide to interpretability techniques that open up the black box of AI. This practical guide simplifies cutting edge research into transparent and explainable AI, delivering practical methods you can easily implement with Python and opensource libraries. With examples from all major machine leaing approaches, this book demonstrates why some approaches to AI are so opaque, teaches you toidentify the pattes your model has leaed, and presents best practices for building fair and unbiased models.How deep leaing models produce their results is often a complete mystery, even to their creators. These AI”black boxes” can hide unknown issues―including data leakage, the replication of human bias, and difficulties complying with legal requirements such as the EU’s “right to explanation.” State-of-the-art interpretability techniques have been developed to understand even the most complex deep leaing models, allowing humans to follow an AI’s methods and to better detect when it has made a mistake.
Review “I think this is a valuable book both for beginners as well for more experienced users.”Kim Falk Jørgensen“This book provides a great insight into the interpretability step of developing a structured leaing robust AI systems.” IzharHaq“Really great introduction to interpretability of ML models as well asgreat examples of how you can do it to your own models.” JonathanWood“Techniques are consistently presented with excellent examples.” JamesJ. Byleckie“A fine book towards making ML models less opaque.” AlainCouniot“Read this to understand what the model actually says about the underlying data.” Shashank Polasa“Everybody working with ML models should be able to interpret (and check) results. This book will help you with that.” KaiGellien From the Back Cover Interpretable AI is a hands-on guide to interpretability techniques that open up the black box of AI. This practical guide simplifies cutting-edge research into transparent and explainable AI, delivering practical methods you can easily implement with Python and open source libraries. With examples from all major machine leaing approaches, this book demonstrates why some approaches to AI are so opaque, teaches you to identify the pattes your model has leaed, and presents best practices for building fair and unbiased models. When you’re done, you’ll be able to improve your AI’s performance during training, and build robust systems that counter act errors from bias, data leakage, and concept drift.
About the Author
Ajay Thampi is a machine leaing engineer at a large tech company primarily focused on responsible AI and faiess. He holds a PhD and his research was focused on signal processing and machine leaing. He has published papers at leading conferences and jouals on reinforcement leaing, convex optimization, and classical machine leaing techniques applied to 5G cellular networks.