Optimization of Number of Neurons in the Hidden Layer in Feed Forward Neural Networks with an Emphasis to Cascade Correlation Networks

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

Modified one-Parameter Lindley Distribution and Its Applications

In this paper a new one-parameter lifetime distribution named “Modified One-Parameter Lindley Distribution” which is a modification of Lindley Distribution, with an increasing hazard rate for modeling lifetime data has b...

Robotic Arm Control For Collecting Liquid Aerosol Samples Using Microcontroller

A PIC18f452 Microcontroller Based Robotic Arm For Collection Of Liquid Aerosol Samples Has Been Design And Developed. Robotic Arm Is Designed For Collecting 32 Number Of Liquid Samples In Which The Liquid Aerosol Samples...

Flight Attitude Controller Using Dynamic Inversion Theory with Stability Margin Guarantee

In order to realize reusable launch vehicle, flight attitude control system is important. Dynamic inversion (DI) theory is known well as nonlinear control theory. DI theory can cancel the nonlinear dynamics and linearize...

Penetration Testing An Effective And Versatile Tool For Software Security

Software is being developed and released for public utility in applications of mobile phone technologies to aircraft and spaceship explorations at a very fast pace which requires proper testing prior to their release so...

A Review on Fluoride in Ground Water: Causes, Effects and Solutions

Water, the most vital resource for all kinds of life on this planet, is also the resource, adversely affected both quantitatively and qualitatively by all kind of human activities on land, in air or in water or naturally...

Download PDF file
  • EP ID EP392105
  • DOI -
  • Views 94
  • Downloads 0

How To Cite

Dr. R. Amal Raj (2017). Optimization of Number of Neurons in the Hidden Layer in Feed Forward Neural Networks with an Emphasis to Cascade Correlation Networks. International Journal of engineering Research and Applications, 7(9), 20-30. https://europub.co.uk/articles/-A-392105