Title: Combinatorial Machine Learning Creativity

Matthew Guzdial

Ph.D. Student

School of Interactive Computing

College of Computing

Georgia Institute of Technology

Date: Tuesday, November 14 2017

Time: 3:00 - 5:00PM (EDT)

Location: TSRB 222

Committee:

Dr. Mark Riedl (Advisor, School of Interactive Computing, Georgia Institute of Technology)

Dr. Ashok Goel (School of Interactive Computing, Georgia Tech)

Dr. Charles Isbell (School of Interactive Computing, Georgia Tech)

Dr. Brian Magerko (School of Literature, Media, Communication, Georgia Tech)

Dr. Devi Parikh (School of Interactive Computing, Georgia Tech

Dr. Michael Mateas (Computational Media Department, University of California, Santa Cruz)

Abstract:

We propose the application of techniques from the field of creativity research to machine learned models. The techniques in question are combinatorial creativity techniques, defined as techniques that combine two sets of input to create novel output sets. In this way combinatorial machine learning creativity can produce new ML models without any training data. We present combinatorial machine learning creativity applied in the domain of video games and propose future applications in other domains.