000			02073cam a2200325 i 4500
001			s53c6bw7qd07q56c
003			SE-LIBR
005			20221117094935.0
008			201110s2020 nyu||||||b||||001 0|eng|
020			_a9780393635829
020			_z9780393635836 ((epub)
040			_aZ _dOCLCO _dOCLCF _dUAP _dYDX _dCPP _dTCH _dZ _dSipr
041			_aeng
100	1		_aChristian, Brian, _d1984-
245	1	4	_aThe alignment problem : _bmachine learning and human values / _cBrian Christian
250			_aFirst edition 2020.
260			_aNorton : _bNew York, NY, _c2021
300			_axii, 476 pages _c25 cm
500			_a"First published as a Norton paperback 2021"
504			_aIncludes bibliographical references (pages [401]-451) and index.
520			_a"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"--
650		0	_asocial sciences
650		0	_acomputers _xsafety
650		7	_aartificial intelligence _xethics
653			_asoftware failures
653			_amachine learning
653			_amoral and ethical aspects
852			_h621.39 Christian
942			_cMONO
999			_c80255 _d80255