1 option
Responsible AI : Implementing Ethical and Unbiased Algorithms / by Sray Agarwal, Shashin Mishra.
- Format:
- Book
- Author/Creator:
- Agarwal, Sray, Author.
- Mishra, Shashin, Author.
- Series:
- Computer Science (SpringerNature-11645)
- Language:
- English
- Subjects (All):
- Artificial intelligence.
- Machine learning.
- Technology-Moral and ethical aspects.
- Computers and civilization.
- Artificial intelligence-Data processing.
- Computers.
- Artificial Intelligence.
- Machine Learning.
- Ethics of Technology.
- Computers and Society.
- Data Science.
- Computing Milieux.
- Local Subjects:
- Artificial Intelligence.
- Machine Learning.
- Ethics of Technology.
- Computers and Society.
- Data Science.
- Computing Milieux.
- Physical Description:
- 1 online resource (XIX, 177 pages) : 143 illustrations, 132 illustrations in color.
- Edition:
- 1st ed. 2021.
- Contained In:
- Springer Nature eBook
- Place of Publication:
- Cham : Springer International Publishing : Imprint: Springer, 2021.
- System Details:
- text file PDF
- 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.
- Contents:
- 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.
- Other Format:
- Printed edition:
- ISBN:
- 978-3-030-76860-7
- 9783030768607
- Access Restriction:
- Restricted for use by site license.
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.