Email RIS file
Bookmark
Report an Issue

The alignment problem : machine learning and human values / Brian Christian

Author
Christian, Brian, 1984-
Additional Titles
Machine learning and human values
Published
New York, NY : W.W. Norton & Company, [2020]
Edition
First edition.
Physical Description
xii, 476 pages ; 25 cm

Availability

Browse Nearby on Shelf
I Want It
I Want It

Finding items...

Contents
Prophecy. Representation -- Fairness -- Transparency -- Agency. Reinforcement -- Shaping -- Curiosity -- Normativity. Imitation -- Inference -- Uncertainty.
Summary
"A jaw-dropping exploration of everything that goes wrong when we build AI systems-and the movement to fix them. Today's "machine-learning" systems, trained by data, are so effective that we've invited them to see and hear for us-and to make decisions on our behalf. But alarm bells are ringing. Systems cull résumés until, years later, we discover that they have inherent gender biases. Algorithms decide bail and parole-and appear to assess black and white defendants differently. We can no longer assume that our mortgage application, or even our medical tests, will be seen by human eyes. And autonomous vehicles on our streets can injure or kill. When systems we attempt to teach will not, in the end, do what we want or what we expect, ethical and potentially existential risks emerge. Researchers call this the alignment problem. In best-selling author Brian Christian's riveting account, we meet the alignment problem's "first-responders," and learn their ambitious plan to solve it before our hands are completely off the wheel"--Provided by publisher.
Subject(s)
ISBN
9780393635829 hardcover
0393635821 hardcover
Bibliography Note
Includes bibliographical references (pages [401]-451) and index.
Endowment Note
Hrinya Family Libraries Endowment for the School of Information Sciences and Technology
James and Joyce Gettys Libraries Endowment in the Math Library and in the School of Information Sciences and Technology
View MARC record | catkey: 33517051