Optimization of Number of Neurons in the Hidden Layer in Feed Forward Neural Networks with an Emphasis to Cascade Correlation Networks
Journal Title: International Journal of engineering Research and Applications - Year 2017, Vol 7, Issue 9
Abstract
The architectures of Artificial Neural Networks (ANN) are based on the problem domain and it is applied during the „training phase‟ of sample data and used to infer results for the remaining data in the testing phase. Normally, the architecture consist of three layers as input, hidden, output layers with the number of nodes in the input layer as number of known values on hand and the number of nodes as result to be computed out of the values of input nodes and hidden nodes as the output layer. The number of nodes in the hidden layer is heuristically decided so that the optimum value is obtained with reasonable number of iterations with other parameters with its default values. This study mainly focuses on Cascade-Correlation Neural Networks (CCNN) using Back-Propagation (BP) algorithm which finds the number of neurons during the training phase itself by appending one from the previous iteration satisfying the error condition gives a promising result on the optimum number of neurons in the hidden layer.
Authors and Affiliations
Dr. R. Amal Raj
Keywords
Related Articles
- EP ID EP392105
- DOI -
- Views 109
- Downloads 0
A study on ‘CSR Implementation in the Vicinity of a Manufacturing Location- Midterm Impact Assessment of Four On-going Projects’
.
Bioremediation of oil-polluted coastal soils of the Caspian Sea with active oil-oxidizing associations
Model studies on the purification of oil-polluted coastal soil by bacterial and bacterial-yeast associations were carried out. It is established that when they are introduced, changes in the composition of the microbioce...
Evaluation Of Bituminous Mix Parameters With Addition Of Plastic Waste
Road construction is the main integral part of the developing countries. The conventional method has been proven perfect for the road construction but now, time has come where there is a need of enhancement of properties...
Performance Analysis of Spatially Multiplexed MIMO using STBC Antenna Diversity Technique
A new wireless broadband technology, MIMO (multiple input multiple output) systems, has gained great popularity for faster data transmission speed and have been actively investigated and successfully deployed for the eme...
Application of soft computing techniques in dental Image Segmentation
Image segmentation is a very important and pre-processing step in image analysis. The conventional multilevel thresholding methods are efficient for bi-level thresholding because of its simplicity, robustness, less conve...