2009 Special Issue: Neural networks with multiple general neuron models: A hybrid computational intelligence approach using Genetic Programming

  • Authors:

  • Alan J. Barton;Julio J. Valdés;Robert Orchard

  • Affiliations:

  • Knowledge Discovery Group, Institute for Information Technology, National Research Council Canada, Ottawa, Ontario, Canada;Knowledge Discovery Group, Institute for Information Technology, National Research Council Canada, Ottawa, Ontario, Canada;Knowledge Discovery Group, Institute for Information Technology, National Research Council Canada, Ottawa, Ontario, Canada

  • Venue:
  • Neural Networks
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Classical neural networks are composed of neurons whose nature is determined by a certain function (the neuron model), usually pre-specified. In this paper, a type of neural network (NN-GP) is presented in which: (i) each neuron may have its own neuron model in the form of a general function, (ii) any layout (i.e network interconnection) is possible, and (iii) no bias nodes or weights are associated to the connections, neurons or layers. The general functions associated to a neuron are learned by searching a function space. They are not provided a priori, but are rather built as part of an Evolutionary Computation process based on Genetic Programming. The resulting network solutions are evaluated based on a fitness measure, which may, for example, be based on classification or regression errors. Two real-world examples are presented to illustrate the promising behaviour on classification problems via construction of a low-dimensional representation of a high-dimensional parameter space associated to the set of all network solutions.