02346cam a2200313 i 4500 PIMLIB 20250418092406.0 241218s2020 nyu b 001 0 eng 2020029036 9780393868333 9780393635829 (hardcover) 9780393635836 (epub) Q334.7 .C488A 2020 Christian, Brian, 1984- author. 63972 The Alignment problem : machine learning and human values / Brian Christian. New York, NY : W.W. Norton & Company, 2020 xii, 476 pages ; 25 cm. Includes bibliographical references (pages [401]-451) and index. "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. Artificial Intelligence Moral and ethical aspects. 28335 Artificial Intelligence Social aspects. 28335 Machine learning Safety measures. 38969 Software failures. 101198 Social values. 101199 50113 0100 สำนักอธิการบดี 7 cbc orignew 1 ecip 20 y-gencatlg lcc BK 0 1 1001587 1001587 0 0 lcc 0 0 BKCh PIMLIB PIMLIB GEN-EN 2024-12-18 บริษัท บุ๊คเน็ท จำกัด 985.00 01300000151091 12 1 6 Q334.7 .C488A 2020 32550000521990 2025-11-25 2025-04-18 2025-04-18 837.25 2024-12-18 BK