Academic Journals Database
Disseminating quality controlled scientific knowledge

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

ADD TO MY LIST
 
Author(s): Ana Carolina Sousa Silva | Sergio Souto | Euvaldo Ferreira Cabral Jr. | Ernane Jose Xavier Costa

Journal: Research Journal of Biological Sciences
ISSN 1815-8846

Volume: 2;
Issue: 5;
Start page: 607;
Date: 2007;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Calculable copmplexit | artificial neurm model | complexity measurement | performance | multilayer

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.
Save time & money - Smart Internet Solutions     

Tango Rapperswil
Tango Rapperswil