Welcome to the InfoSci Platform
Fast Learning in Neural Networks

Fast Learning in Neural Networks

Darryl Charles, Colin Fyfe, Daniel Livingstone, Stephen McGlinchey
Copyright: © 2008 |Pages: 14
ISBN13: 9781591406464|ISBN10: 1591406463|ISBN13 Softcover: 9781616926854|EISBN13: 9781591406488
DOI: 10.4018/978-1-59140-646-4.ch006
Cite Chapter Cite Chapter

MLA

Charles, Darryl, et al. "Fast Learning in Neural Networks." Biologically Inspired Artificial Intelligence for Computer Games, edited by Darryl Charles, et al., IGI Global, 2008, pp. 91-104. https://doi.org/10.4018/978-1-59140-646-4.ch006

APA

Charles, D., Fyfe, C., Livingstone, D., & McGlinchey, S. (2008). Fast Learning in Neural Networks. In D. Charles, C. Fyfe, D. Livingstone, & S. McGlinchey (Eds.), Biologically Inspired Artificial Intelligence for Computer Games (pp. 91-104). IGI Global. https://doi.org/10.4018/978-1-59140-646-4.ch006

Chicago

Charles, Darryl, et al. "Fast Learning in Neural Networks." In Biologically Inspired Artificial Intelligence for Computer Games, edited by Darryl Charles, et al., 91-104. Hershey, PA: IGI Global, 2008. https://doi.org/10.4018/978-1-59140-646-4.ch006

Export Reference

Mendeley
Favorite

Abstract

We noted in the previous chapters that, while the multilayer perceptron is capable of approximating any continuous function, it can suffer from excessively long training times. In this chapter we will investigate methods of shortening training times for artificial neural networks using supervised learning. (Haykin, 1999) is a particularly good reference for radial basis function, RBF, networks. In this chapter we outline the theory and implementation of a RBF network before demonstrating how such a network may be used to solve one of the previously visited problems, and compare our solutions.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.