Applying Bayesian Regularization for Acceleration of Levenberg-Marquardt based Neural Network Training

Author
Keywords
Abstract
Neural network is widely used for image classification problems, and is proven to be effective with high successful rate. However one of its main challenges is the significant amount of time it takes to train the network. The goal of this research is to improve the neural network training algorithms and apply and test them in classification and recognition problems. In this paper, we describe a method of applying Bayesian regularization to improve Levenberg-Marquardt (LM) algorithm and make it better usable in training neural networks. In the experimental part, we qualify the modified LM algorithm using Bayesian regularization and use it to determine an appropriate number of hidden layers in the network to avoid overtraining. The result of the experiment was very encouraging with a 98.8% correct classification when run on test samples.
Year of Publication
2018
Journal
International Journal of Interactive Multimedia and Artificial Intelligence
Volume
5
Issue
Regular Issue
Number
1
Number of Pages
68-72
Date Published
06/2018
ISSN Number
1989-1660
Citation Key
URL
DOI
Attachment