Evolution of Cartesian Genetic Programs for Development of Learning Neural Architecture

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "Gul Muhammad Khan and Julian F. Miller and 
                 David M. Halliday",
  title =        "Evolution of Cartesian Genetic Programs for
                 Development of Learning Neural Architecture",
  journal =      "Evolutionary Computation",
  year =         "2011",
  volume =       "19",
  number =       "3",
  pages =        "469--523",
  keywords =     "genetic algorithms, genetic programming, cartesian
                 genetic programming, Artificial Neural Networks, ANN,
                 Co-evolution, Generative and developmental approaches,
                 Learning and memory",
  ISSN =         "1063-6560",
  DOI =          "doi:10.1162/EVCO_a_00043)",
  size =         "55 pages",
  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 subcomponents
                 of biological neurons and demonstrate that intelligent
                 behaviour 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 neuron consists of
                 a collection of seven chromosomes encoding distinct
                 computational functions inside 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
                 executing repeatedly 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.",

Genetic Programming entries for Gul Muhammad Khan Julian F Miller David M Halliday