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
Gravity Lamp
In recent times due to effects of pollution and global warming there is a need for generating power from renewable sources. The reason for generating power using gravity is that it is available all over the Earth, abunda...
Segmenting the Character of Plate Vehicle Number Using Connected Component Analysis Method
The introduction of vehicle number plates is one of the important techniques as part of an intelligent transportation system that can be used to identify a vehicle simply by understanding the license plate. The introduct...
Structural Run Based Feature Vector to Classify Printed Tamil Characters Using Neural Network
Feature Extraction plays most crucial and important role in character recognition. The selection of stable and representative set of features is the main problem in pattern recognition. Because of font characteristics an...
Some Fixed Points Theorems
In this research paper we have proved a fixed point theorem by taking a function to be an upper semi-continuous function from right. This theorem uses a function from the set of all positive real numbers to itself. Thus...
Application of Queuing Model in the Hospital Pharmacy Unit-A Case Study
The Objective Of This Study Was To Analyze Various Design Alternatives In Determining The Manpower Requirements Needed To Run A Hospital’s Pharmacy Unit Efficiently. Several Queuing Models Are Used For This Analysis. Thi...