TY  - JOUR
T1  - Using an Easy Calculable Complexity Measure to Introduce Complexity in the Artificial Neuron Model
AU - , Ana Carolina Sousa Silva AU - , Sergio Souto AU - , Euvaldo Ferreira Cabral Jr. AU - , Ernane Jose Xavier Costa 
JO  - Research Journal of Biological Sciences
VL  - 2
IS  - 5
SP  - 607
EP  - 611
PY  - 2007
DA  - 2001/08/19
SN  - 1815-8846
DO  - rjbsci.2007.607.611
UR  - https://makhillpublications.co/view-article.php?doi=rjbsci.2007.607.611
KW  - Calculable copmplexit
KW  -artificial neurm model
KW  -complexity measurement
KW  -performance
KW  -multilayer
AB  - 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.
ER  -