Evolution of cartesian genetic programs for development of learning neural architecture

  • Authors:

  • Gul Muhammad Khan;Julian F. Miller;David M. Halliday

  • Affiliations:

  • Electrical Engineering Department, NWFP UET Peshawar, Pakistan. gk502@nwfpuet.edu.pk;Electronics Department, University of York, York, YO10 5DD, UK. jfm7@ohm.york.ac.uk;Electronics Department, University of York, York, YO10 5DD, UK. dh20@ohm.york.ac.uk

  • Venue:
  • Evolutionary Computation
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Although artificial neural networks have taken their inspiration from natural neurological systems, they have largely ignored the genetic basis of neural functions. Indeed, evolutionary approaches have mainly assumed that neural learning is associated with the adjustment of synaptic weights. The goal of this paper is to use evolutionary approaches to find suitable computational functions that are analogous to natural sub-components of biological neurons and demonstrate that intelligent behavior can be produced as a result of this additional biological plausibility. Our model allows neurons, dendrites, and axon branches to grow or die so that synaptic morphology can change and affect information processing while solving a computational problem. The compartmental model of a neuron consists of a collection of seven chromosomes encoding distinct computational functions inside the neuron. Since the equivalent computational functions of neural components are very complex and in some cases unknown, we have used a form of genetic programming known as Cartesian genetic programming (CGP) to obtain these functions. We start with a small random network of soma, dendrites, and neurites that develops during problem solving by repeatedly executing the seven chromosomal programs that have been found by evolution. We have evaluated the learning potential of this system in the context of a well-known single agent learning problem, known as Wumpus World. We also examined the harder problem of learning in a competitive environment for two antagonistic agents, in which both agents are controlled by independent CGP computational networks (CGPCN). Our results show that the agents exhibit interesting learning capabilities.