IMPACT OF WEIGHT INITIALIZATION ON TRAINING OF SIGMOIDAL FFANN
Journal Title: ICTACT Journal on Soft Computing - Year 2018, Vol 8, Issue 3
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 and Affiliations
Bhatia M P S, Pravin Chandra
Keywords
Related Articles
- EP ID EP532533
- DOI 10.21917/ijsc.2018.0236
- Views 59
- Downloads 0
ENHANCED NEIGHBORHOOD NORMALIZED POINTWISE MUTUAL INFORMATION ALGORITHM FOR CONSTRAINT AWARE DATA CLUSTERING
Clustering of similar data items is an important technique in mining useful patterns. To enhance the performance of Clustering, training or learning is an important task. A constraint learning semi-supervised methodology...
A NOVEL APPROACH FOR LONG TERM SOLAR RADIATION PREDICTION
With present stress, being laid on green energy worldwide, harnessing solar energy for commercial use has importance in sizing and long-term prediction of solar radiation. However, with continuous changing environment pa...
LOSSLESS TEXT COMPRESSION FOR UNICODE TAMIL DOCUMENTS
Data compressions for different world languages including Indian languages are in high need and demand. Tamil language is one of the longest-surviving classical languages in the world. Usage of Tamil language for communi...
AN QUALITY BASED ENHANCEMENT OF USER DATA PROTECTION VIA FUZZY RULE BASED SYSTEMS IN CLOUD ENVIRONMENT
So far, in cloud computing distinct customer is accessed and consumed enormous amount of services through web, offered by cloud service provider (CSP). However cloud is providing one of the services is, security-as-a-ser...
FUZZY LOGIC BASED HYBRID RECOMMENDER OF MAXIMUM YIELD CROP USING SOIL, WEATHER AND COST
Our system is designed to predict best suitable crops for the region of farmer. It also suggests farming strategies for the crops such as mixed cropping, spacing, irrigation, seed treatment, etc. along with fertilizer an...