Open AccessFORMING EVOLUTIONARY DESIGN OF NEURAL NETWORKS WITH DIFFERENT NODES
Author(s) -
Eva Volná
Publication year - 2014
Publication title -
computing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.184
H-Index - 11
eISSN - 2312-5381
pISSN - 1727-6209
DOI - 10.47839/ijc.8.1.652
Subject(s) - neuroevolution , computer science , artificial neural network , feedforward neural network , artificial intelligence , time delay neural network , evolutionary algorithm , stochastic neural network , coding (social sciences) , evolutionary acquisition of neural topologies , mathematics , statistics
Evolution in artificial neural networks (e.g. neuroevolution) searches through the space of behaviours for a network that performs well at a given task. Here is presented a neuroevolution system evolving populations of neurons that are combined to form the fully connected multilayer feedforward neural network with fixed architecture. In this article, the transfer function has been shown to be an important part of architecture of the artificial neural network and have significant impact on an artificial neural network’s performance. In order to test the efficiency of described method, we applied it to the pattern recognition problem and to the alphabet coding problem.