TY - JOUR
KW - Neural Network
KW - Image Classification
KW - Levenberg-Marquardt Method
KW - Pattern Clustering
AU - Azizah Suliman
AU - Batyrkhan Omarov
AB - 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.
IS - Regular Issue
M1 - 1
N2 - 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.
PY - 2018
SP - 68
EP - 72
T2 - International Journal of Interactive Multimedia and Artificial Intelligence
TI - Applying Bayesian Regularization for Acceleration of Levenberg-Marquardt based Neural Network Training
UR - http://www.ijimai.org/journal/sites/default/files/files/2018/04/ijimai_5_1_9_pdf_32121.pdf
VL - 5
SN - 1989-1660
ER -