THE ALIGNMENT PROBLEM : How Can Artificial Intelligence Learn Human Values? /
Christian, Brian,
THE ALIGNMENT PROBLEM : How Can Artificial Intelligence Learn Human Values? / by Brian Christian. - 476 pages : 20 cm.
Includes index.
Includes bibliography (pages 402 - 451)
The Alignment Problem: Machine Learning and Human Values is a 2020 non-fiction book by the American writer Brian Christian. It is based on numerous interviews with experts trying to build artificial intelligence systems, particularly machine learning systems, that are aligned with human values.
9781786494337 Paperback 9781786494320
Computers
Social Aspects--Science
Artificial intelligence --Moral and ethical aspects
Social aspects--Ethical problems
Human-computer interaction
Machine learning--Safety measures
Software failures
006.3 / BRI
THE ALIGNMENT PROBLEM : How Can Artificial Intelligence Learn Human Values? / by Brian Christian. - 476 pages : 20 cm.
Includes index.
Includes bibliography (pages 402 - 451)
The Alignment Problem: Machine Learning and Human Values is a 2020 non-fiction book by the American writer Brian Christian. It is based on numerous interviews with experts trying to build artificial intelligence systems, particularly machine learning systems, that are aligned with human values.
9781786494337 Paperback 9781786494320
Computers
Social Aspects--Science
Artificial intelligence --Moral and ethical aspects
Social aspects--Ethical problems
Human-computer interaction
Machine learning--Safety measures
Software failures
006.3 / BRI