Generalization across contexts in unsupervised computational creativity

Debarun Bhattacharjya, Dharmashankar Subramanian, Lav R. Varshney

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Autonomous computational creativity systems must not only have the ability to generate artifacts, but also to select the best ones on the basis of some assessment of quality (and novelty). Such quality functions are typically directly encoded using domain knowledge or learned through supervised learning algorithms using labeled training data. Here we introduce the notion of unsupervised computational creativity; we specifically consider the possibility of unsupervised assessment for a given context by generalizing artifact relationships learned across all contexts. A particular approach that uses a knowledge graph for generalizing rules from an inspiration set of artifacts is demonstrated through a detailed example of computational creativity for causal associations in civic life, drawing on an event dataset from political science. Such a system may be used by analysts to help imagine future worlds.

Original languageEnglish (US)
Title of host publicationProceedings of the 9th International Conference on Computational Creativity, ICCC 2018
EditorsFrancois Pachet, Anna Jordanous, Carlos Leon
PublisherAssociation for Computational Creativity (ACC)
Pages40-47
Number of pages8
ISBN (Electronic)9789895416004
StatePublished - 2018
Event9th International Conference on Computational Creativity, ICCC 2018 - Salamanca, Spain
Duration: Jun 25 2018Jun 29 2018

Publication series

NameProceedings of the 9th International Conference on Computational Creativity, ICCC 2018

Conference

Conference9th International Conference on Computational Creativity, ICCC 2018
CountrySpain
CitySalamanca
Period6/25/186/29/18

ASJC Scopus subject areas

  • Computational Theory and Mathematics

Fingerprint Dive into the research topics of 'Generalization across contexts in unsupervised computational creativity'. Together they form a unique fingerprint.

Cite this