Interactive construction of loading algorithm with Genetic Programming
Abstract
This paper integrates an interactive framework into Automatic Construction technique of Loading Algorithms based on Cartesian Genetic Programing (ACLA-CGP). While ACLA-CGP has a capacity to derive a loading algorithm optimizing a given objective function, its validity still remains unclear under human evaluations. Our interactive ACLA-CGP, i.e., i-ACLA-CGP, is designed to reduce human evaluations as possible and thus evaluates’ burdens. Experimental results show that i-ACLA-CGP successfully derives loading algorithms with 50 human evaluations while satisfying their preferences.
Publication
Annual Conference on Electronics, Information, and Systems, pp. 197–202
Notice
- All materials on this page are author’s versions, not necessarily coincide with final published versions.
Kei Nishihara
2nd-year Doctoral Student
My research interests include evolutionary computation and swarm intelligence.