Informing artificial intelligence generative techniques using cognitive theories of human creativity

Steve Dipaola, Liane Gabora, G. McCaig

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

19 Citations (Scopus)

Abstract

The common view that our creativity is what makes us uniquely human suggests that incorporating research on human creativity into generative deep learning techniques might be a fruitful avenue for making their outputs more compelling and human-like. Using an original synthesis of DeepDream-based convolutional neural networks and cognitive based computational art rendering systems, we show how honing theory, intrinsic motivation, and the notion of a "seed incident" can be implemented computationally, and demonstrate their impact on the resulting generative art. Conversely, we discuss how explorations in deep learning convolutional neural net generative systems can inform our understanding of human creativity. We conclude with ideas for further cross-fertilization between AI based computational creativity and psychology of creativity.

Original languageEnglish
Title of host publicationProcedia Computer Science
Pages158-168
Number of pages11
Volume145
DOIs
Publication statusPublished - 2018
Event Annual International Conference on Biologically Inspired Cognitive Architectures - Czech Technical University in Prague, Prague, Czech Republic
Duration: 22 Aug 201824 Aug 2018

Publication series

NameProcedia Computer Science

Conference

Conference Annual International Conference on Biologically Inspired Cognitive Architectures
Country/TerritoryCzech Republic
CityPrague
Period22/08/1824/08/18

Keywords

  • Cognitive Science
  • Computational Creativity
  • Deep Learning

Fingerprint

Dive into the research topics of 'Informing artificial intelligence generative techniques using cognitive theories of human creativity'. Together they form a unique fingerprint.

Cite this