From inspired modeling to creative modeling

Daniel Cohen-Or, Hao Zhang

Research output: Contribution to journalArticlepeer-review


An intriguing and reoccurring question in many branches of computer science is whether machines can be creative, like humans. Evolutionary algorithms (EAs) have played the most dominant role in creative modeling so far. They are inspired by biological evolution in nature, which features mutation and cross-over of DNAs, as well as selection. The element of surprise or unpredictability, which is central to creative modeling, arises from the stochasticity embedded in the mutation, recombination (cross-over), and selection operators of an EA. A straightforward way to introduce surprises is for each creator to work independently from the others. If the creations were executed in a sequence, then one creator would not know what previous creators had produced, increasing the likelihood of unexpectedness in the current creation. Some efforts on co-creativity-driven content creation have been geared towards the more artistic and open-ended tasks in creating 2D abstract art work and movement-based performances. A delicate balance has to be struck between controllability, based on functional as well as physical design criteria, and creativity arising from the co-creation paradigm.

Original languageEnglish
Pages (from-to)7-14
Number of pages8
JournalVisual Computer
Issue number1
StatePublished - Jan 2016

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'From inspired modeling to creative modeling'. Together they form a unique fingerprint.

Cite this