Items related to The Alignment Problem: How Can Machines Learn Human...
Synopsis
'Vital reading. This is the book on artificial intelligence we need right now.' Mike Krieger, cofounder of Instagram
Artificial intelligence is rapidly dominating every aspect of our modern lives influencing the news we consume, whether we get a mortgage, and even which friends wish us happy birthday. But as algorithms make ever more decisions on our behalf, how do we ensure they do what we want? And fairly?
This conundrum - dubbed 'The Alignment Problem' by experts - is the subject of this timely and important book. From the AI program which cheats at computer games to the sexist algorithm behind Google Translate, bestselling author Brian Christian explains how, as AI develops, we rapidly approach a collision between artificial intelligence and ethics. If we stand by, we face a future with unregulated algorithms that propagate our biases - and worse - violate our most sacred values. Urgent and fascinating, this is an accessible primer to the most important issue facing AI researchers today.
"synopsis" may belong to another edition of this title.
About the Author
Brian Christian is the author of the acclaimed bestsellers The Most Human Human and Algorithms to Live By, which have been translated into nineteen languages. A visiting scholar at the University of California, Berkeley, he lives in San Francisco.
From the Back Cover
Artificial intelligence is rapidly dominating every aspect of our modern lives influencing the news we consume, whether we get a mortgage, and even which friends wish us happy birthday. But as algorithms make ever more decisions on our behalf, how do we ensure they do what we want? And fairly? This conundrum - dubbed 'The Alignment Problem' by experts - is the subject of this timely and important book. From the AI program which cheats at computer games to the sexist algorithm behind Google Translate, bestselling author Brian Christian explains how, as AI develops, we rapidly approach a collision between artificial intelligence and ethics. If we stand by, we face a future with unregulated algorithms that propagate our biases - and worse - violate our most sacred values. Urgent and fascinating, this is an accessible primer to the most important issue facing AI researchers today.
"About this title" may belong to another edition of this title.
Other Popular Editions of the Same Title
Search results for The Alignment Problem: How Can Machines Learn Human...
Stock Image
The Alignment Problem: How Can Machines Learn Human Values?
Published by
Atlantic Books 21/01/2021, 2021
ISBN 10: 1786494302
ISBN 13: 9781786494306
Used
Hardcover
Seller: Bahamut Media, Reading, United Kingdom
Seller rating 5 out of 5 stars
Hardcover. Condition: Very Good. Shipped within 24 hours from our UK warehouse. Clean, undamaged book with no damage to pages and minimal wear to the cover. Spine still tight, in very good condition. Remember if you are not happy, you are covered by our 100% money back guarantee. Seller Inventory # 6545-9781786494306
Quantity: 1 available
Stock Image
The Alignment Problem: How Can Machines Learn Human Values?
Seller: AwesomeBooks, Wallingford, United Kingdom
Seller rating 5 out of 5 stars
Hardcover. Condition: Very Good. The Alignment Problem: How Can Machines Learn Human Values? This book is in very good condition and will be shipped within 24 hours of ordering. The cover may have some limited signs of wear but the pages are clean, intact and the spine remains undamaged. This book has clearly been well maintained and looked after thus far. Money back guarantee if you are not satisfied. See all our books here, order more than 1 book and get discounted shipping. . Seller Inventory # 7719-9781786494306
Quantity: 1 available
Seller Image
The Alignment Problem: How Can Machines Learn Human Values?
Seller: WeBuyBooks, Rossendale, LANCS, United Kingdom
Seller rating 5 out of 5 stars
Condition: Very Good. Most items will be dispatched the same or the next working day. A copy that has been read, but is in excellent condition. Pages are intact and not marred by notes or highlighting. The spine remains undamaged. Seller Inventory # wbs3612994511
Quantity: 1 available
Stock Image
The Alignment Problem: How Can Machines Learn Human Values?
Seller: WorldofBooks, Goring-By-Sea, WS, United Kingdom
Seller rating 5 out of 5 stars
Paperback. Condition: Very Good. The book has been read, but is in excellent condition. Pages are intact and not marred by notes or highlighting. The spine remains undamaged. Seller Inventory # GOR011952023
Quantity: 2 available
Stock Image
The Alignment Problem: How Can Machines Learn Human Values?
Seller: medimops, Berlin, Germany
Seller rating 5 out of 5 stars
Condition: as new. Wie neu/Like new. Seller Inventory # M01786494302-N
Quantity: 1 available