Evolving neural networks using attribute grammars

The evolutionary optimization of neural networks involves two main design issues: how the neural network is represented genetically, and how that representation is manipulated through genetic operations. We have developed a genetic representation that uses an attribute grammar to encode both topological and architectural information about a neural network. We have defined genetic operators that are applied to the parse trees formed by the grammar. These operators provide the ability to introduce selection strategies that vary during the course of evolution