Record Details

Web Based Software for Back Propagation Neural Network with Weight Decay

KrishiKosh

View Archive Info
 
 
Field Value
 
Title Web Based Software for Back Propagation Neural Network with Weight Decay
M C A
 
Creator Rakesh kumar ranjan
 
Contributor Anu Sharma
 
Subject Web Based Software : Neural Network: Weight Decay
 
Description T-8746
The rapid advancements in the internet technology front have expanded the potentiality for web based software packages. Web based software allows quick and convenient sharing of methodology among researchers. Keeping in pace with the development of the internet technology, there is need to develop web based data analysis tools in agriculture research also.
Artificial Neural Networks (ANNs) are non-linear structures used for prediction and classification problems. ANNs can identify and learn correlated patterns between input data sets and corresponding target values. Trained ANN can be used to predict the outcomes of independent variables. Over fitting and under fitting are two major problems that may arise in ANNs. Multi-collinearity is a statistical phenomenon in which two or more predictor variables in a model are highly correlated and provide redundant information about the response. The problem of multi-collinearity leads to overtraining. This problem is handled by using artificial neural networks with weight decay algorithm.
Most of the software available for analyzing the data using ANN is either very costly or difficult to use. This study attempt to develop a free web based software for back propagation neural networks with weight decay algorithm. Waterfall model has been used for software development process. This software is useful for statistician and researchers working in the area of agriculture.
 
Date 2016-08-27T13:21:27Z
2016-08-27T13:21:27Z
2012
 
Type Thesis
 
Identifier http://krishikosh.egranth.ac.in/handle/1/74089
 
Format application/pdf
 
Publisher IARI , Indian Agricultural Statistics Research Institute