Particle Swarm Optimization for Creating Self Organized Evolutionary Back Propagation Artificial Neural Networks

Shivnath Ghosh, Santanu Koley (2015) “Particle Swarm Optimization for creating self organized Evolutionary Back Propagation Artificial Neural Networks” VCAN-2015 April 18-19, 2015, An International Conference on VLSI, communication and Networks Alwar, Rajasthan, ISBN: 978-93-84869-55-7, pp. 256-259

6 Pages Posted: 28 Nov 2016

See all articles by Shivnath Ghosh

Shivnath Ghosh

The IIS University

Santanu Koley

Budge Budge Institute of Technology

Date Written: December 21, 2015

Abstract

A novel technique for developing a self organized Back Propagation Artificial Neural Networks (BPANNs) or simply Back Propagation Neural Network (BPN) with the help of swarm Intelligence (SI) technique. This paper proposes an overlapping swarm intelligence algorithm for training of neural networks in which a particle swarm is assigned to each neuron to search for that neuron’s weights. The training of ANN is a difficult task when it’s get into the local minima and causes the low learning rates; it is required of an evolutionary multi dimensional algorithm to seek optimal weight values, the positional optimum values and the dimensional optimum in values in the dynamic problem space. The approach discussed throughout in this paper is the credit assignment process by first focusing on updating weights and biases swarms Intelligence and then evaluating the fitness of the particles using a network. With the proper adaptation of the SI-BPN process, the proposed method can develop an optimum network within an architecture space for a particular problem. Additionally, it provides a class list of all other potential configurations. This algorithm will provide superior learning ability to the traditional Back-Propagation (BP) method in terms of accuracy and speed.

Keywords: Swarms Intelligence, Artificial Neural Networks, Back Propagation Neural Network, Learning rates, Local minima, Problem space

Suggested Citation

Ghosh, Shivnath and Koley, Santanu, Particle Swarm Optimization for Creating Self Organized Evolutionary Back Propagation Artificial Neural Networks (December 21, 2015). Shivnath Ghosh, Santanu Koley (2015) “Particle Swarm Optimization for creating self organized Evolutionary Back Propagation Artificial Neural Networks” VCAN-2015 April 18-19, 2015, An International Conference on VLSI, communication and Networks Alwar, Rajasthan, ISBN: 978-93-84869-55-7, pp. 256-259, Available at SSRN: https://ssrn.com/abstract=2873677 or http://dx.doi.org/10.2139/ssrn.2873677

Shivnath Ghosh

The IIS University ( email )

Gurukul Marg
SFS, Mansarovar
Jaipur, 302020
India

Santanu Koley (Contact Author)

Budge Budge Institute of Technology ( email )

Nischintapur
Budge Budge
Kolkata, WA
India

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
24
Abstract Views
227
PlumX Metrics