Human-Guided Learning for Probabilistic Logic Models

Simple item page
dc.contributor.authorOdom, P.
dc.contributor.authorNatarajan, Sriraam
dc.contributor.utdAuthorNatarajan, Sriraam
dc.date.accessioned2019-08-01T22:31:11Z
dc.date.available2019-08-01T22:31:11Z
dc.date.created2018-06-25
dc.description.abstractAdvice-giving has been long explored in the artificial intelligence community to build robust learning algorithms when the data is noisy, incorrect or even insufficient. While logic based systems were effectively used in building expert systems, the role of the human has been restricted to being a "mere labeler" in recent times. We hypothesize and demonstrate that probabilistic logic can provide an effective and natural way for the expert to specify domain advice. Specifically, we consider different types of advice-giving in relational domains where noise could arise due to systematic errors or class-imbalance inherent in the domains. The advice is provided as logical statements or privileged features that are thenexplicitly considered by an iterative learning algorithm at every update. Our empirical evidence shows that human advice can effectively accelerate learning in noisy, structured domains where so far humans have been merely used as labelers or as designers of the (initial or final) structure of the model.
dc.description.departmentErik Jonsson School of Engineering and Computer Science
dc.description.sponsorshipWe gratefully acknowledge the support of CwC Program Contract W911NF-15-1-0461 with the US Defense Advanced Research Projects Agency (DARPA) and the Army Research Office (ARO).
dc.identifier.bibliographicCitationOdom, P., and S. Natarajan. 2018. "Human-guided learning for probabilistic logic models." Frontiers in Robotics and AI 5: art. 56, doi:10.3389/frobt.2018.00056
dc.identifier.issn2296-9144
dc.identifier.urihttps://hdl.handle.net/10735.1/6767
dc.identifier.volume5
dc.language.isoen
dc.publisherFrontiers Media S.A.
dc.relation.urihttp://dx.doi.org/10.3389/frobt.2018.00056
dc.rightsCC BY 4.0 (Attribution)
dc.rights©2018 The Authors
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.source.journalFrontiers in Robotics and AI
dc.subjectKnowledge-based systems (Computer science)
dc.subjectConfidential communications
dc.subjectArtificial intelligence--Statistical methods
dc.titleHuman-Guided Learning for Probabilistic Logic Models
dc.type.genrearticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
JECS-6766-279899.60.pdf
Size:
1.53 MB
Format:
Adobe Portable Document Format
Description:
Article
Download

Collections

Natarajan, Sriraam