Responsible AI : implementing ethical and unbiased algorithms / Sray Agarwal, Shashin Mishra.
Agarwal, Sray, author.; Mishra, Shashin, author.
2021
Q336 .A43 2021
Available Online

Linked e-resources

Linked Resource Online Access
Concurrent users Unlimited
Authorized users Authorized users
Document Delivery Supplied Can lend chapters, not whole ebooks

Details

Title Responsible AI : implementing ethical and unbiased algorithms / Sray Agarwal, Shashin Mishra.
Author Agarwal, Sray, author.
ISBN 9783030768607 (electronic bk.)
3030768600 (electronic bk.)
9783030769772
3030769771
9783030768591
3030768597
DOI https://doi.org/10.1007/978-3-030-76860-7
Published Cham : Springer, [2021]
Copyright ©2021
Language English
Description 1 online resource (xix, 177 pages) : illustrations (chiefly color)
Other Standard Identifiers 10.1007/978-3-030-76860-7 doi
Call Number Q336 .A43 2021
Dewey Decimal Classification 006.3
Summary This book is written for software product teams that use AI to add intelligent models to their products or are planning to use it. As AI adoption grows, it is becoming important that all AI driven products can demonstrate they are not introducing any bias to the AI-based decisions they are making, as well as reducing any pre-existing bias or discrimination. The responsibility to ensure that the AI models are ethical and make responsible decisions does not lie with the data scientists alone. The product owners and the business analysts are as important in ensuring bias-free AI as the data scientists on the team. This book addresses the part that these roles play in building a fair, explainable and accountable model, along with ensuring model and data privacy. Each chapter covers the fundamentals for the topic and then goes deep into the subject matter--providing the details that enable the business analysts and the data scientists to implement these fundamentals. AI research is one of the most active and growing areas of computer science and statistics. This book includes an overview of the many techniques that draw from the research or are created by combining different research outputs. Some of the techniques from relevant and popular libraries are covered, but deliberately not drawn very heavily from as they are already well documented, and new research is likely to replace some of it. Hands-on approach to ensure easy practical implementation of the concepts discussed Most of the techniques covered are new, with only a few that refer to existing packages. For the techniques covered, the book goes deep into the subject matter and includes code to help the product teams implement these techniques for their products Also addresses the contribution that product owners and the business analysts make to the product being fair and explainable, explaining every topic in detail, including the math involved Covers the end-to-end view of what any software product team needs to do to be able to create a robust, successful and fair AI-driven product Most of the chapters include notes sections throughout to cover the topic in progress for all audiences. Non-technical readers will also benefit by the introductions and conclusions for the book and in each of the chapters.
Bibliography, etc. Note Includes bibliographical references.
Access Note Access limited to authorized users.
Digital File Characteristics text file
PDF
Source of Description Online resource; title from PDF title page (SpringerLink, viewed September 28, 2021).
Added Author Mishra, Shashin, author.
Available in Other Form Print version: 9783030769772
Linked Resources Online Access
Record Appears in Online Resources > Ebooks
All Resources
Introduction
Fairness and proxy features
Bias in data
Explainability
Remove bias from ML model
Remove bias from ML output
Accountability in AI
Data and model privacy
Conclusion.

Browse Subjects

Show more subjects...

Statistics

from
to
Export