2014 |
Volume 2 |
Issue 1
Comparative Study of Adaptive Learning Rate with Momentum and Resilient Back Propagation Algorithms for Neural Net Classifier Optimization
1.
Saduf Afzal
– Department Of Computer Sciences,university Of Kashmir, Srinagar, India.
2.
Mohd. Arif Wani
– Department Of Computer Sciences,university Of Kashmir, Srinagar, India.
Received
14-Aug-2014
|
Accepted
-
|
Published
14-Aug-2014
|
Abstract
Learning algorithms are generally used to optimize the convergence of neural networks. We need to optimize the convergence of neural networks in order to increase the speed and accuracy of decision making process. One such algorithm that is used to facilitate the optimization process is back propagation
learning algorithm. The objective of this study is to compare the performance of two variations of back propagation learning algorithm (Adaptive learning rate with momentum and Resilient). Both the algorithms are experimented on a variety of classification problems in order to assess the efficiency of these two learning approaches. Experimental results reveal that during testing and training Resilient propagation algorithm outperforms back propagation with Adaptive learning rate and momentum.
Keywords ANN, Back-propagation, RPROP, Learning Rate , Momentum
Locked
Subscribed
Open Access
