000 01463nam a22003737a 4500
001 557
003 MBIP
005 20250422102930.0
008 250206b |||||||| |||| 00| 0 eng d
020 _a9781786494337
_qRM 67.70
_cPaperback
020 _a9781786494320
_qebook
020 _z1786494337
040 _aMBIP
_beng
_cMBIP
_dNF
_erda
082 0 4 _223
_a006.3
_bBRI
100 1 _aChristian, Brian,
_eauthor.
245 1 0 _aTHE ALIGNMENT PROBLEM :
_bHow Can Artificial Intelligence Learn Human Values? /
_cby Brian Christian.
264 1 _aLondo :
_bAtlantic Books,
_c2021
264 4 _c©2020
300 _a476 pages :
_c20 cm.
336 _2rdacontent
_atext
337 _2rdamedia
_aunmediated
338 _2rdacarrier
_avolume
500 _aIncludes index.
504 _aIncludes bibliography (pages 402 - 451)
520 _aThe 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.
650 0 _aComputers
650 0 _aSocial Aspects
_vScience
650 0 _aArtificial intelligence
_vMoral and ethical aspects
650 0 _aSocial aspects
_vEthical problems
650 0 _aHuman-computer interaction
650 0 _aMachine learning
_vSafety measures
650 0 _aSoftware failures
942 _2ddc
_cBK
_n0
999 _c1051
_d1051