Using Genetic Engineering To Find Modular Structures for Architectures of Artificial Neural Networks

Starting with an evolutionary algorithm to optimize the architecture of an artificial neural network (ANN), it will be shown that it is possible, with the help of a graph database and genetic engineering, to find modular structures for these networks. A new graph rewriting is used to construct families of architectures from these modular structures. Simulation results for two problems are given. This technique can be useful as an alternative to automatic defined functions for computing intensive structure optimization problems, where modularity is needed.