000			02346cam a2200313 i 4500
003			PIMLIB
005			20250418092406.0
008			241218s2020 nyu b 001 0 eng
010			_a2020029036
020			_a9780393868333
020			_a9780393635829 _q(hardcover)
020			_z9780393635836 _q(epub)
050	0	0	_aQ334.7 _b.C488A _y2020
100			_aChristian, Brian, _d1984- _eauthor. _963972
245	1	4	_aThe Alignment problem : _bmachine learning and human values / _cBrian Christian.
264		1	_aNew York, NY : _bW.W. Norton & Company, _c2020
300			_axii, 476 pages ; _c25 cm.
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"-- _cProvided by publisher.
650		0	_aArtificial Intelligence _xMoral and ethical aspects. _928335
650		0	_aArtificial Intelligence _xSocial aspects. _928335
650		0	_aMachine learning _xSafety measures. _938969
650		0	_aSoftware failures. _9101198
650		0	_aSocial values. _9101199
690			_950113 _a0100 สำนักอธิการบดี
906			_a7 _bcbc _corignew _d1 _eecip _f20 _gy-gencatlg
942			_2lcc _cBK _n0 _01
999			_c1001587 _d1001587