IMPACT OF WEIGHT INITIALIZATION ON TRAINING OF SIGMOIDAL FFANN

Abstract
During training one of the most important factor is weight initialization that affects the training speed of the neural network. In this paper we have used random and Nguyen-Widrow weight initialization along with the proposed weight initialization methods for training the FFANN. We have used various types of data sets as input. Five data sets are taken from UCI machine learning repository. We have used PROP Back-Propagation algorithms for training and testing. We have taken different number of inputs and hidden layer nodes with single output node for experimentation. We have found that in almost all the cases the proposed weight initialization method gives better results.

Authors
M P S Bhatia1, Veenu2, Pravin Chandra3
Netaji Subhas Institute of Technology, India1,2, Guru Gobind Singh Indraprastha University, India3

Keywords
Feed Forward Artificial Neural Network, Back-Propagation Algorithm, Weight Initialization
Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 8 , Issue: 3 )
Date of Publication :
April 2018

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.