Seminar: Modelling Evolvability and Robustness in Genetic Programming

Benjamin Fowler
Ph.D. Oral Comprehensive
Supervisory Committee: Dr. Wolfgang Banzhaf, Dr. Yuanzhu Chen and Dr. Orland Hoeber

Modelling Evolvability and Robustness in Genetic Programming

Department of Computer Science
Wednesday, Jan. 7, 2015, 11:00a.m., Room EN 2022


Abstract

I propose to develop a tree-based genetic programming system, capable of modelling evolvability and robustness during evolution through machine learning algorithms, and exploiting those models to increase the efficiency and final fitness of the system. Existing methods of determining evolvability and robustness require too much computational time to be effective in any practical sense. By being able to model them instead, the computational time to compute them may be reduced, and using them to select more appropriately during evolution will be pragmatic. This will be done first by demonstrating the effectiveness of modelling these properties *a priori*, before expanding the system to show their effectiveness as evolution occurs.