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

View Sample PDF

Author(s): Juan Ramón Rabuñal Dopico (University of Coruña, Spain), Javier Pereira Loureiro (University of Coruña, Spain)and Mónica Miguélez Rico (University of Coruña, Spain)
Copyright: 2009
Pages: 20
Source title: Advancing Artificial Intelligence through Biological Process Applications
Source Author(s)/Editor(s): Ana B. Porto Pazos (Coruna University, Spain), Alejandro Pazos Sierra (Coruna University, Spain)and Washington Buño Buceta (Cajal Institute, Spanish Council for Scientific Research, Spain)
DOI: 10.4018/978-1-59904-996-0.ch005

Keywords: Biologically-Inspired Computing / Biotechnology and Bioinformatics / Engineering Science Reference / Medicine & Healthcare

Purchase

View Simulation of the Action Potential in the Neuron's Membrane in Artificial Neural Networks on the publisher's website for pricing and purchasing information.

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.

The IRMA Community

Research IRM

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

Purchase

Abstract

Related Content

IRMA Sponsors