Learning how to reinterpret creative problems
Kazjon S. Grace, John S. Gero, Rob Saunders · 2013
This paper discusses a method, implemented in the do-main of computational association, by which computa-tional creative systems could learn from their previous experiences and apply them to influence their future be-haviour, even on creative problems that differ signifi-cantly from those encountered before. The approach is based on learning ways that problems can be reinter-preted. These interpretations may then be applicable to other problems in ways that specific solutions or object knowledge may not. We demonstrate a simple proof-of-concept of this approach in the domain of simple visual association, and discuss how and why this behaviour could be integrated into other creative systems.