Learning polynomial feedforward neural networks by genetic programming and backpropagation

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@Article{ieee-nn:Nikolaev+Iba:2003,
  author =       "Nikolay Y. Nikolaev and H. Iba",
  title =        "Learning polynomial feedforward neural networks by
                 genetic programming and backpropagation",
  journal =      "IEEE Transactions on Neural Networks",
  year =         "2003",
  type =         "Paper",
  volume =       "14",
  month =        mar,
  pages =        "337--350",
  number =       "2",
  keywords =     "genetic algorithms, genetic programming, Atmospheric
                 modelling, Backpropagation algorithms, Biological
                 system modeling, Feedforward neural networks,
                 Multilayer perceptrons, Neural networks, Polynomials,
                 Power system modeling, Predictive models,
                 backpropagation, feedforward neural nets, genetic
                 algorithms, learning (artificial intelligence),
                 multilayer perceptrons, Volterra models,
                 backpropagation, feedforward neural networks, genetic
                 programming, learning, multilayer perceptrons,
                 polynomial activation, polynomial feedforward neural
                 networks, polynomial network structure, time series
                 prediction",
  ISSN =         "1045-9227",
  DOI =          "doi:10.1109/TNN.2003.809405",
  abstract =     "This paper presents an approach to learning polynomial
                 feedforward neural networks (PFNNs). The approach
                 suggests, first, finding the polynomial network
                 structure by means of a population-based search
                 technique relying on the genetic programming paradigm,
                 and second, further adjustment of the best discovered
                 network weights by an especially derived
                 backpropagation algorithm for higher order networks
                 with polynomial activation functions. These two stages
                 of the PFNN learning process enable us to identify
                 networks with good training as well as generalisation
                 performance. Empirical results show that this approach
                 finds PFNN which outperform considerably some previous
                 constructive polynomial network algorithms on
                 processing benchmark time series.",
}

Genetic Programming entries for Nikolay Nikolaev Hitoshi Iba

Citations