Simulation of the Action Potential in the Neuron’s Membrane in Artificial Neural Networks - Advancing Artificial Intelligence Through Biological Process Applications - page 75

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

Juan Ramón Rabuñal Dopico
University of Coruña, Spain

Javier Pereira Loureiro
University of Coruña, Spain

Mónica Miguélez Rico
University of Coruña, Spain

AbSTRACT

In this chapter, we state an evolution of the Recurrent ANN (RANN) to enforce the persistence of acti-
vations 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.

INTRODUCTION

this moment, the more wide used RANN were
Hopfield networks and Boltzman machines that
weren't effective to treat dynamic problems. The
powerful of this new type of RANN is based on
the increment of the number of connections and
the whole recursivity of the network. These char-
acteristics, however, increment the complexity of
the training algorithms and the time to finish the
convergence process. These problems have slow

Due to the limitation of the classical ANN mod-
els (Freeman, 1993) to manage time problems,
over the year 1985 began the development of
recurrent models (Pearlmutter, 1990) capable to
solve efficiently this kind of problems. But this
situation didn't change until the arrival of the
Recurrent Backpropagation algorithm. Before