Accession Number:

ADA522046

Title:

Evolving Artificial Neural Networks with Generative Encodings Inspired by Developmental Biology

Descriptive Note:

Doctoral thesis

Corporate Author:

MICHIGAN STATE UNIV EAST LANSING DEPT OF COMPUTER SCIENCE/ENGINEERING

Personal Author(s):

Report Date:

2010-01-01

Pagination or Media Count:

124.0

Abstract:

In this dissertation I investigate the difference between generative encodings and direct encodings for evolutionary algorithms. Generative encodings are inspired by developmental biology and were designed, in part, to increase the regularity of synthetically evolved phenotypes. Regularity is an important design principle in both natural organisms and engineered designs. The majority of this dissertation focuses on how the property of regularity enables a generative encoding to outperform direct encoding controls, and whether a bias towards regularity also hurts the performance of the generative encoding on some problems. I also report on whether researchers can bias the types of regularities produced by a generative encoding to accommodate user preferences. Finally, I study the degree to which a generative encoding produces another important design principle, modularity. Several previous studies have shown that generative encodings outperform direct encodings on highly regular problems. However, prior to this dissertation, it was not known how generative encodings compare to direct encodings on problems with different levels of regularity. On three different problems, I show that a generative encoding can exploit intermediate amounts of problem regularity, which enabled the generative encoding to increasingly outperform direct encoding controls as problem regularity increased. This performance gap emerged because the generative encoding produced regular artificial neural networks ANNs that produced regular behaviors. The ANNs evolved with the generative encoding contained a diverse array of complicated, regular neural wiring patterns, whereas the ANNs produced by a direct encoding control were irregular. I also document that the bias towards regularity can hurt a generative encoding on problems that have some amount of irregularity.

Subject Categories:

  • Computer Programming and Software
  • Cybernetics
  • Anatomy and Physiology

Distribution Statement:

APPROVED FOR PUBLIC RELEASE