Welcome to the InfoSci Platform
Reference Hub1
Evolving Graphs for ANN Development and Simplification

Evolving Graphs for ANN Development and Simplification

Daniel Rivero, David Periscal
Copyright: © 2009 |Pages: 7
ISBN13: 9781599048499|ISBN10: 1599048493|EISBN13: 9781599048505
DOI: 10.4018/978-1-59904-849-9.ch094
Cite Chapter Cite Chapter

MLA

Rivero, Daniel, and David Periscal. "Evolving Graphs for ANN Development and Simplification." Encyclopedia of Artificial Intelligence, edited by Juan Ramón Rabuñal Dopico, et al., IGI Global, 2009, pp. 618-624. https://doi.org/10.4018/978-1-59904-849-9.ch094

APA

Rivero, D. & Periscal, D. (2009). Evolving Graphs for ANN Development and Simplification. In J. Rabuñal Dopico, J. Dorado, & A. Pazos (Eds.), Encyclopedia of Artificial Intelligence (pp. 618-624). IGI Global. https://doi.org/10.4018/978-1-59904-849-9.ch094

Chicago

Rivero, Daniel, and David Periscal. "Evolving Graphs for ANN Development and Simplification." In Encyclopedia of Artificial Intelligence, edited by Juan Ramón Rabuñal Dopico, Julian Dorado, and Alejandro Pazos, 618-624. Hershey, PA: IGI Global, 2009. https://doi.org/10.4018/978-1-59904-849-9.ch094

Export Reference

Mendeley
Favorite

Abstract

One of the most successful tools in the Artificial Intelligence (AI) world is Artificial Neural Networks (ANNs). This technique is a powerful tool used in many different environments, with many different purposes, like classification, clustering, signal modelization, or regression (Haykin, 1999). Although they are very easy to use, their creation is not a simple task, because the expert has to do much effort and spend much time on it. The development of ANNs can be divided into two parts: architecture development and training and validation. The architecture development determines not only the number of neurons of the ANN, but also the type of the connections among those neurons. The training determines the connection weights for such architecture. The architecture design task is usually performed by means of a manual process, meaning that the expert has to test different architectures to find the one able to achieve the best results. Each architecture trial means training and validating it, which can be a process that needs many computational resources, depending on the complexity of the problem. Therefore, the expert has much participation in the whole ANN development, although techniques for relatively automatic creation of ANNs have been recently developed.

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.