The University of Sussex

Incremental evolution of neural network architectures for adaptive behaviour

D. Cliff, I. Harvey, P. Husbands

This paper describes aspects of our ongoing work in evolving recurrent dynamical artificial neural networks which act as sensory-motor controllers, generating adaptive behaviour in artificial agents. We start with a discussion of the rationale for our approach. Our approach involves the use of recurrent networks of artificial neurons with rich dynamics, resilience to noise (both internal and external); and separate excitation and inhibition channels. The networks allow artificial agents (simulated or robotic) to exhibit adaptive behaviour. The complexity of designing networks built from such units leads us to use our own extended form of genetic algorithm, which allows for incremental automatic evolution of controller-networks. Finally, we review some of our recent results, applying our methods to work with simple visually-guided robots. The genetic algorithm generates useful network architectures from an initial set of randomly-connected networks. During evolution, uniform noise was added to the activation of each neuron. After evolution, we studied two evolved networks, to see how their performance varied when the noise range was altered. Significantly, we discovered that when the noise was eliminated, the performance of the networks degraded: the networks use noise to operate efficiently.

Download compressed postscript file