7 records matched your query
02098aam a2200313 i 4500 001 D7E840CCE97711ED8437380758ECA4DB 003 SILO 005 20230503010033 008 210129t20212020nyu e b 001 0 eng d 020 $a 0393868338 020 $a 9780393868333 035 $a (OCoLC)1233266753 040 $a YDX $b eng $e rda $c YDX $d JUH $d SILO 100 1 $a Christian, Brian, $d 1984- $e author. 245 14 $a The alignment problem : $b machine learning and human values / $c Brian Christian. 264 1 $a New York, NY : $b W.W. Norton & Company, $c [2021] 300 $a xvi, 476 pages ; $c 21 cm 504 $a Includes bibliographical references (pages [401]-451) and index. 520 $a 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 reÌsumeÌs 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 author Brian Christian's 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. 505 0 $a Representation -- Fairness -- Transparency -- Reinforcement -- Shaping -- Curiosity -- Imitation -- Inference -- Uncertainty. 650 0 $a Artificial intelligence. 650 0 $a Machine learning. 650 0 $a Software failures. 650 0 $a Social values. 941 $a 3 952 $l TYPH572 $d 20240524010235.0 952 $l UNUX074 $d 20240416012012.0 952 $l S1PD771 $d 20230503010844.0 956 $a http://locator.silo.lib.ia.us/search.cgi?index_0=id&term_0=D7E840CCE97711ED8437380758ECA4DBInitiate Another SILO Locator Search