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

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...

Full description

Saved in:
Bibliographic Details
Published in:International journal of interactive multimedia and artificial intelligence Vol. 5; no. 1; pp. 68 - 72
Main Authors: Suliman, Azizah, Omarov, Batyrkhan
Format: Journal Article
Language:English
Published: IMAI Software 01.06.2018
Subjects:
Algorithms
Artificial neural networks
Image Classification
Levenberg
Marquardt Method
Neural Network
Pattern Clustering
ISSN:1989-1660, 1989-1660
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1989-1660
1989-1660
DOI:10.9781/ijimai.2018.04.004