Abstract: Determining the parameters of a Radial Basis Function Neural Network (number of neurons, and their respective centers and radii) is often done by hand, or based in methods highly dependent on initial values. In this work, Evolutionary Algorithms are used to automatically build a RBF NN that solves a specified problem. The evolutionary algorithms are implemented using a new evolutionary computation framework called EO, which allows direct evolution of problem solutions, so that no internal representation is needed, and specific solution domain knowledge can beused to construct evolutionary operators, as well as cost or fitness functions. Results show that this new approach finds nets with good generalization power, while maintaining a reasonable size.
Publication Year: 2001
Publication Date: 2001-01-01
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
Cited By Count: 5
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot