Research Journal of Biological Sciences

94
Views

0
Downloads

Using an Easy Calculable Complexity Measure to Introduce Complexity in the Artificial Neuron Model

Ana Carolina Sousa Silva , Sergio Souto , Euvaldo Ferreira Cabral Jr. and Ernane Jose Xavier Costa
Page: 607-611 | Received 21 Sep 2022, Published online: 21 Sep 2022

By Research Area

Medicine & Public Health Life Sciences Engineering Mathematics Biomedicine Physics Chemistry Computer Science Earth Sciences Social Sciences Business and Management Psychology Materials Science Economics Education Environment Philosophy Statistics Law Political Science and International Relations Pharmacy Dentistry Energy Linguistics Geography Finance Criminology and Criminal Justice Medicine Cultural and Media Studies History Architecture / Design Literature Biomedical Sciences Religious Studies Education & Language Food Science & Nutrition Public Health

By Volume and Issue

Abstract

This study introduces an approach to simulate neural complexity by changing the McCulloch and Pitts neuron model. The new approach was tested by comparing the classification performance of a multilayer perceptron with complexity measurement capability to a traditional multilayer perceptron with McCulloch and Pitts neuron model The results showed that the multilayer perceptron implemented with the complexity measurement approach achieved best classification performance (worst score of 94%) when compared with multilayer perceptron without the complexity approach (best score of 51%) in task of classifier large time series generated by a logistic map with different generator parameter.

How to cite this article:

Ana Carolina Sousa Silva , Sergio Souto , Euvaldo Ferreira Cabral Jr. and Ernane Jose Xavier Costa . Using an Easy Calculable Complexity Measure to Introduce Complexity in the Artificial Neuron Model.
DOI: https://doi.org/10.36478/rjbsci.2007.607.611
URL: https://www.makhillpublications.co/view-article/1815-8846/rjbsci.2007.607.611