LEADER 00000cgm a2200469 i 4500 003 OCoLC 005 20240129213017.0 006 m o c 007 cr cna|||||||| 007 vz czazuu 008 191114s2019 xx 040 o vleng d 029 1 AU@|b000066431084 035 (OCoLC)1127579404 037 CL0501000082|bSafari Books Online 040 UMI|beng|erda|epn|cUMI|dOCLCF|dTOH|dOCLCO|dOCLCQ|dOCLCO 049 INap 099 Streaming Video O’Reilly for Public Libraries 100 1 Poursabzi-Sangdeh, Forough,|eon-screen presenter. 245 10 Manipulating and Measuring Model Interpretability / |cForough Poursabzi-Sangdeh.|h[O'Reilly electronic resource] 264 1 [Place of publication not identified] :|bO'Reilly Media, |c2019. 300 1 online resource (1 streaming video file (39 min., 42 sec.)) 336 two-dimensional moving image|btdi|2rdacontent 337 computer|bc|2rdamedia 337 video|bv|2rdamedia 338 online resource|bcr|2rdacarrier 500 Title from resource description page (Safari, viewed November 12, 2019). 511 0 Presenter, Forough Poursabzi-Sangdeh. 520 "Machine learning is increasingly used to make decisions that affect people's lives in critical domains like criminal justice, fair lending, and medicine. While most of the research in machine learning focuses on improving the performance of models on held-out datasets, this is seldom enough to convince end users that these models are trustworthy and reliable in the wild. To address this problem, a new line of research has emerged that focuses on developing interpretable machine learning methods and helping end users make informed decisions. Despite the growing body of work in developing interpretable models, there is still no consensus on the definition and quantification of interpretability ... Forough approaches the problem of interpretability from an interdisciplinary perspective built on decades of research in psychology, cognitive science, and social science to understand human behavior and trust. She describes a set of controlled user experiments in which researchers manipulated various design factors in models that are commonly thought to make them more or less interpretable and measured their influence on users' behavior."--Resource description page 590 O'Reilly|bO'Reilly Online Learning: Academic/Public Library Edition 650 0 Machine learning. 650 0 Artificial intelligence. 650 2 Artificial Intelligence 650 6 Apprentissage automatique. 650 6 Intelligence artificielle. 650 7 artificial intelligence.|2aat 650 7 Artificial intelligence.|2fast|0(OCoLC)fst00817247 650 7 Machine learning.|2fast|0(OCoLC)fst01004795 655 4 Electronic videos. 711 2 O'Reilly Artificial Intelligence Conference|d(15-18 April 2019 :|cNew York, N.Y.)|jissuing body. 856 40 |uhttps://ezproxy.naperville-lib.org/login?url=https:// learning.oreilly.com/videos/~/0636920339724/?ar|zAvailable for O'Reilly for Public Libraries 994 92|bJFN