Network Generating Attribute Grammar Encoding

Talib S. Hussain and Roger A. Browse

Abstract

The development and theoretical analysis of neural network architectures may be improved with the availability of techniques which allow the systematic representation and generation of classes of architectures. Recent work on the genetic optimization of neural networks has led to new ideas on how to encode neural network architectures abstractly as grammars. Extending this approach, we have devised an encoding system that uses an attribute grammar in which the evaluation of both synthesized and inherited attributes within a generated parse tree provides the details of the connectivity of the network. Comparison with cellular encoding and the geometry-oriented variation of cellular encoding suggests that attribute grammar encoding is simpler, easier to use, and has more potential as a technique for effectively generating neural networks.