Discovery of General Learning Rules for Feedforward Neural Networks with Step Activation Function using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@TechReport{radi:CSRP-99-1,

• author = "Amr M. Radi and Riccardo Poli",
• title = "Discovery of General Learning Rules for Feedforward Neural Networks with Step Activation Function using Genetic Programming",
• institution = "University of Birmingham, School of Computer Science",
• number = "CSRP-99-1",
• month = jan,
• year = "1999",
• file = "/1999/CSRP-99-01.ps.gz",
• URL = "ftp://ftp.cs.bham.ac.uk/pub/tech-reports/1999/CSRP-99-01.ps.gz",
• reportfilename = "pub/tech-reports/1999/CSRP-99-01.ps.gz",
• keywords = "genetic algorithms, genetic programming",
• abstract = "No standard learning algorithm exists for training neural networks with step activation function. In this work we use Genetic Programming (GP) to discover supervised learning algorithms which can train neural networks using step function. A new learning algorithm has been discovered and has been shown to provide good performances.",

}

Genetic Programming entries for Amr Mohamed Mahmoud Khairat Radi Riccardo Poli

Citations