Discovering Efficient Learning Rules for Feedforward Neural Networks using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.9137

@TechReport{radi:2002:CSM360,

• author = "Amr Radi and Riccardo Poli",
• title = "Discovering Efficient Learning Rules for Feedforward Neural Networks using Genetic Programming",
• institution = "Department of Computer Science, University of Essex",
• year = "2002",
• number = "CSM-360",
• address = "Colchester, UK",
• month = jan,
• keywords = "genetic algorithms, genetic programming, ANN, Rprop, NLR, TSS, XOR, NMN encoder, MLP, activation functions, logistic regression, hyperbolic tangent, NLP, vowels, sonar, HB, OCR, momentum",
• URL = "http://cswww.essex.ac.uk/technical-reports/2002/csm-360.ps.gz",
• size = "26 pages",
• abstract = "Standard BackPropagation (SBP) algorithm is the most widely known and used learning method for training neural networks. Unfortunately SBP suffers from several problems such as sensitivity to the initial conditions and very slow convergence. Here we describe how we used Genetic Programming, a search algorithm inspired by Darwinian evolution, to discover new supervised learning algorithms for neural networks which can overcome some of these problems. Comparing our new algorithms with SBP on different problems we show that these are faster, are more stable and have greater feature extracting capabilities.",

}

Genetic Programming entries for Amr Mohamed Mahmoud Khairat Radi Riccardo Poli

Citations