Academic Journals Database
Disseminating quality controlled scientific knowledge

A Review on Ensemble of Diverse Artificial Neural Networks

ADD TO MY LIST
 
Author(s): Mittal C. Patel , Prof. Mahesh Panchal

Journal: International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
ISSN 2278-1323

Volume: 1;
Issue: 10;
Start page: 063;
Date: 2012;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Artificial neural network Classifier Combination of Classifiers Diversity Ensemble methods Generalization error Neural Network Ensembles

ABSTRACT
Ensemble Data Mining Methods, also known as Committee Methods or Model Combiners, whichprovides the power of multiple classifiers to achieve better prediction accuracy than any of theindividual classifier could on their own. The diversity among the members of ensemble is used todetermining its generalization error. The empirical results reveal that the performance of anensemble is related to the diversity among individual learners in the ensemble and more diversitymight be used to obtain better performance. Artificial Neural networks(ANN) are very flexible withrespect to incomplete, missing and noisy data and also makes the data to use for dynamicenvironment. ANN is dependent on how best is the configuration of the net in terms of number ofweights, neurons and layers. Diversity in an ensemble of neural networks can be handled bymanipulating either input data or output data.
Save time & money - Smart Internet Solutions      Why do you need a reservation system?