The Alignment Problem
Machine Learning and Human Values
Our rough guess is there are 89,000 words in this book.
At a pace averaging 250 words per minute, this book will take 5 hours and 56 minutes to read. With a half hour per day, this will take 12 days to read.
How long will it take you?
This book will take an estimated to read at a reading speed averaging words per minute. With 30 minutes per day, this will take to read.
Enter your reading speedYou can take one of our WPM reading speed tests to find your reading speed.
Create a free account to track your reading progress, build your reading list, and set reading goals.
Author
Publication
2020-10-06 - W. W. Norton & Company
Word Count
89,000 words, Guess
Page Count
356 pages
Physical Format
Hardcover
Identifiers
- ISBN-100393635821
- ISBN-139780393635829
- Library of Congress Control Number2020029036
- OCLC Control Number1137850003
- Better World Books9780393635829
and 1 more
- Open LibraryOL28126189M
Classifications
- LCCQ334.7.C47 2020
- LCCQ334.7 .C47 2020
Description
"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.
Subjects
Topics
Other Editions
- The Alignment Problem: Machine Learning and Human Values
Show 2 more editions
Similar Books
Reader Reviews
No reviews yet for this book.
Be the first to share your thoughts!