A Neural-Group Basis for Evolving and Developing Neural Networks

Contents

This work investigates an intermediate abstraction level, that of neural groups, for modelling the development of complex artificial neural networks. Based on Edelman's Neural Darwinism, Deacon's Displacement Theory and The Neuromeric Model, our DEACANN system avoids the complexities of axonal and dendritic growth while maintaining key aspects of cell signalling, competition and cooperation that appear to govern the formation of neural topologies in nature. DEACANN also includes a genetic-algorithm for evolving developmental recipes, and the mature networks can employ several forms of learning.