"Why did you do that?": Explaining black box models with Inductive Synthesis

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: WFRF:(McKeever Steve 1969 ) > "Why did you do tha...

LIBRIS Formathandbok (Information om MARC21)

Fältnamn	Indikatorer	Metadata
000		03223naa a2200433 4500
001		oai:DiVA.org:uu-382400
003		SwePub
008		190424s2019 \| \|\|\|\|\|\|\|\|\|\|\|000 \|\|eng\|
024	7	a https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-3824002 URI
024	7	a https://doi.org/10.1007/978-3-030-22750-0_272 DOI
040		a (SwePub)uu
041		a engb eng
042		9 SwePub
072	7	a ref2 swepub-contenttype
072	7	a kon2 swepub-publicationtype
100	1	a Paçacı, Görkem,d 1986-u Uppsala universitet,Institutionen för informatik och media4 aut0 (Swepub:uu)gorpa824
245	1 0	a "Why did you do that?" :b Explaining black box models with Inductive Synthesis
264		c 2019-06-08
264	1	a Cham :b Springer Nature,c 2019
338		a electronic2 rdacarrier
520		a By their nature, the composition of black box models is opaque. This makes the ability to generate explanations for the response to stimuli challenging. The importance of explaining black box models has become increasingly important given the prevalence of AI and ML systems and the need to build legal and regulatory frameworks around them. Such explanations can also increase trust in these uncertain systems. In our paper we present RICE, a method for generating explanations of the behaviour of black box models by (1) probing a model to extract model output examples using sensitivity analysis; (2) applying CNPInduce, a method for inductive logic program synthesis, to generate logic programs based on critical input-output pairs; and (3) interpreting the target program as a human-readable explanation. We demonstrate the application of our method by generating explanations of an artificial neural network trained to follow simple traffic rules in a hypothetical self-driving car simulation. We conclude with a discussion on the scalability and usability of our approach and its potential applications to explanation-critical scenarios.
650	7	a NATURVETENSKAPx Data- och informationsvetenskap0 (SwePub)1022 hsv//swe
650	7	a NATURAL SCIENCESx Computer and Information Sciences0 (SwePub)1022 hsv//eng
653		a artificial intelligence
653		a machine learning
653		a black box models
653		a explanation
653		a inductive logic
653		a program synthesis
700	1	a Johnson, David,d 1979-u Uppsala universitet,Institutionen för informatik och media4 aut0 (Swepub:uu)davjo605
700	1	a McKeever, Steve,d 1969-u Uppsala universitet,Informationssystem4 aut0 (Swepub:uu)stemc181
700	1	a Hamfelt, Andreasu Uppsala universitet,Informationssystem4 aut0 (Swepub:uu)andhamlt
710	2	a Uppsala universitetb Institutionen för informatik och media4 org
773	0	t International Conference on Computational Science (ICCS)d Cham : Springer Nature
856	4	u https://arxiv.org/abs/1904.09273y Pre-print on arXiv
856	4	u https://uu.diva-portal.org/smash/get/diva2:1306760/FULLTEXT01.pdfx primaryx Raw objecty fulltext:postprint
856	4	u http://uu.diva-portal.org/smash/get/diva2:1306760/FULLTEXT01
856	4 8	u https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-382400
856	4 8	u https://doi.org/10.1007/978-3-030-22750-0_27

Till lärosätets databas

Hitta mer i SwePub

Av författaren/redakt...: Paçacı, Görkem, ...; Johnson, David, ...; McKeever, Steve, ...; Hamfelt, Andreas

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...

Artiklar i publikationen: International Co ...

Av lärosätet: Uppsala universitet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se