Biasing the Evolution of Modular Neural Networks
Victor Landassuri, School of Computer Science
Date and time: Thursday 26th May 2011 at 15:00
Location: Room 124, School of Computer Science
Neural networks exist with varying degrees of modularity ranging from pure modular networks characterized by disjoint partitions of hidden nodes with no communication between modules, to pure homogeneous networks with significant connections throughout. In between are apparently homogeneous networks that can be seen to have some degree of modularity if the hidden nodes are reorganized appropriately.
In this talk, a modularity measure is presented and applied to the rearrangement of nodes to create modules in homogeneous networks, and that is used to improve the EPNet algorithm to evolve modular neural networks.
Experimental results on a simple classification task confirm that the new modular EPNet algorithm does indeed lead to more modular networks than the classical EPNet algorithm, without compromising the performance on the given task.