The University of Edinburgh -
Division of Informatics
Forrest Hill & 80 South Bridge

MSc Thesis #9584

Title:Symbiotic Evolution of Neural Networks
Date: 1995
Abstract:The purpose of this dissertation is a, mainly empirical, study of the evolution of neural networks. More precisely, the topology of the nodes, the links, as well as the connection weights of a neural network are to be determined with the aid of a genetic algorithm. The novel approach of the genetic algorithm employed [MM94a] is that it encodes one neuron per chromosome. Therefore, the fitness of a chromosome is determined by its degree of cooperation with other chromosomes as they form a network. An extension of this genetic algorithm has been considered, which allows multi layer feed-forward, as well as recurrent networks. Hence there are no simplifying assumptions concerning the topology of the networks created. The genetic algorithm has been tested on the Iris data set, the two spirals problem and a control problem: the tractor-trailer truck steering problem.

[Search These Pages] [DAI Home Page] [Comment]