000			02941cam a22004817a 4500
001			23248697
003			OSt
005			20250306114240.0
008			230728t20232023caua 001 0 eng d
010			_a 2023278332
015			_aGBC307044 _2bnb
016	7		_a020868348 _2Uk
020			_a9789355422194 (pbk.)
035			_a(OCoLC)on1313074094
040			_aYDX _beng _cYDX _dBDX _dUKMGB _dOCLCQ _dGO9 _dOCLCF _dDLC
042			_alccopycat
050	0	0	_aQ325.5 _b.P78 2023
082	0	4	_a006.31 _223 _bPRU.Y
100	1		_aPruksachatkun, Yada, _eauthor. _931806
245	1	0	_aPracticing trustworthy machine learning : _bconsistent, transparent, and fair AI pipelines / _cby Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar.
246	3		_aConsistent, transparent, and fair artifical intelligence pipelines
250			_a1st ed.
264		1	_aAmerica; _aBoston : _bO'Reilly, _c2023.
264		4	_c©2023
300			_axxiv, 274 p. _billustrations ; _c23 cm
336			_atext _2rdacontent
337			_aunmediated _2rdamedia
338			_avolume _2rdacarrier
500			_aIncludes index.
505	0	0	_tPreface -- _tPrivacy -- _tFairness and bias -- _tModel explainability and interpretability -- _tRobustness -- _tSecure and trustworthy data generation -- _tMore state-of-the-art research questions -- _tFrom theory to practice -- _tAn ecosystem of trust -- _tSynthetic data generation tools -- _tOther interpretability and explainability tool kits -- _tIndex -- _tAbout the authors
520			_aWith the increasing use of AI in high-stakes domains such as medicine, law, and defense, organizations spend a lot of time and money to make ML models trustworthy. Many books on the subject offer deep dives into theories and concepts. This guide provides a practical starting point to help development teams produce models that are secure, more robust, less biased, and more explainable. Authors Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar translate best practices in the academic literature for curating datasets and building models into a blueprint for building industry-grade trusted ML systems. With this book, engineers and data scientists will gain a much-needed foundation for releasing trustworthy ML applications into a noisy, messy, and often hostile world. -- _cProvided by publisher.
650		0	_aMachine learning.
650		0	_aArtificial intelligence _xPhilosophy. _931807
650		0	_aAlgorithms. _931808
650		0	_aData mining.
650		7	_aMachine learning. _2fast _0(OCoLC)fst01004795
700	1		_aMcAteer, Matthew, _eauthor. _931809
700	1		_aMajumdar, Subhabrata, _eauthor. _931810
856	4	2	_zSupplemental information and resources _uhttps://github.com/matthew-mcateer/practicing_trustworthy_machine_learning
906			_a7 _bcbc _ccopycat _d2 _encip _f20 _gy-gencatlg
942			_2ddc _c1 _e23 _n0
999			_c429221 _d429221