Show simple item record

dc.contributor.authorNugent, Conor
dc.contributor.authorCunningham, Padraig
dc.date.accessioned2008-01-15T12:18:25Z
dc.date.available2008-01-15T12:18:25Z
dc.date.issued2004-06-23
dc.identifier.citationNugent, Conor; Cunningham, Padraig. 'A Case-Based Explanation System for `Black-Box? Systems'. - Dublin, Trinity College Dublin, Department of Computer Science, TCD-CS-2004-20, 2004, pp10en
dc.identifier.otherTCD-CS-2004-20
dc.identifier.urihttp://hdl.handle.net/2262/13261
dc.description.abstractMost users of machine-learning products are reluctant to use the systems without any sense of the underlying logic that has led to the system?s predictions. Unfortunately many of these systems lack any transparency in the way they operate and are deemed to be `black boxes?. In this paper we present a Case-Based Reasoning (CBR) solution to providing supporting explanations of black-box systems. This CBR solution uses locally derived feature ranking information that reflects the importance of each feature to a prediction and a locally adjusted case retrieval mechanism. The retrieval mechanism takes advantage of the derived feature weightings to help select cases that are a better reflection of the black-box solution and thus more convincing explanations. ?Computers are useless. They can only give you answers.? - Pablo Picasso.en
dc.format.extent311017 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherTrinity College Dublin, Department of Computer Scienceen
dc.relation.ispartofseriesComputer Science Technical Reporten
dc.relation.ispartofseriesTCD-CS-2004-20en
dc.relation.haspartTCD-CS-[no.]en
dc.subjectComputer Scienceen
dc.titleA Case-Based Explanation System for `Black-Box? Systemsen
dc.typeTechnical Reporten
dc.identifier.rssurihttps://www.cs.tcd.ie/publications/tech-reports/reports.04/TCD-CS-2004-20.pdf


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record