Welcome to the InfoSci Platform
Simulation of the Action Potential in the Neuron's Membrane in Artificial Neural Networks

Simulation of the Action Potential in the Neuron's Membrane in Artificial Neural Networks

Juan Ramón Rabuñal Dopico, Javier Pereira Loureiro, Mónica Miguélez Rico
Copyright: © 2009 |Pages: 20
ISBN13: 9781599049960|ISBN10: 1599049961|ISBN13 Softcover: 9781616925376|EISBN13: 9781599049977
DOI: 10.4018/978-1-59904-996-0.ch005
Cite Chapter Cite Chapter

MLA

Rabuñal Dopico, Juan Ramón, et al. "Simulation of the Action Potential in the Neuron's Membrane in Artificial Neural Networks." Advancing Artificial Intelligence through Biological Process Applications, edited by Ana B. Porto Pazos, et al., IGI Global, 2009, pp. 74-93. https://doi.org/10.4018/978-1-59904-996-0.ch005

APA

Rabuñal Dopico, J. R., Pereira Loureiro, J., & Miguélez Rico, M. (2009). Simulation of the Action Potential in the Neuron's Membrane in Artificial Neural Networks. In A. Porto Pazos, A. Pazos Sierra, & W. Buño Buceta (Eds.), Advancing Artificial Intelligence through Biological Process Applications (pp. 74-93). IGI Global. https://doi.org/10.4018/978-1-59904-996-0.ch005

Chicago

Rabuñal Dopico, Juan Ramón, Javier Pereira Loureiro, and Mónica Miguélez Rico. "Simulation of the Action Potential in the Neuron's Membrane in Artificial Neural Networks." In Advancing Artificial Intelligence through Biological Process Applications, edited by Ana B. Porto Pazos, Alejandro Pazos Sierra, and Washington Buño Buceta, 74-93. Hershey, PA: IGI Global, 2009. https://doi.org/10.4018/978-1-59904-996-0.ch005

Export Reference

Mendeley
Favorite

Abstract

In this chapter, we state an evolution of the Recurrent ANN (RANN) to enforce the persistence of activations within the neurons to create activation contexts that generate correct outputs through time. In this new focus we want to file more information in the neuron’s connections. To do this, the connection’s representation goes from the unique values up to a function that generates the neuron’s output. The training process to this type of ANN has to calculate the gradient that identifies the function. To train this RANN we developed a GA based system that finds the best gradient set to solve each problem.

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.