Analysis of pattern classification for the multidimensional parity-bit-checking problem with hybrid evolutionary feed-forward neural network

Authors:
Manish Mangal;Manu Pratap Singh
Affiliations:
Department of Computer Science, Institute of Computer & Information Science, Dr. B.R. Ambedkar University, Khandari Campus, Agra, UP, India;Department of Computer Science, Institute of Computer & Information Science, Dr. B.R. Ambedkar University, Khandari Campus, Agra, UP, India
Venue:
Neurocomputing
Year:
2007

Citing 3
Cited 4

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Simulations combining evolution and learning

Adaptive individuals in evolving populations
Evolutionary Computation: A New Transactions

IEEE Transactions on Evolutionary Computation

Pattern recalling analysis of English alphabets using Hopfield model of feedback neural network with evolutionary searching

International Journal of Business Information Systems
Performance evaluation of feed-forward neural network with soft computing techniques for hand written English alphabets

Applied Soft Computing
Study of Hopfield neural network with sub-optimal and random GA for pattern recalling of English characters

Applied Soft Computing
Performance evaluation of Hopfield neural networks for overlapped English characters by using genetic algorithms

International Journal of Hybrid Intelligent Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper describes the simulation of two hybrid evolutionary algorithms (EAs) to the feedforward neural networks (NNs) used in classification problems. Besides backpropagation algorithm, simple genetic algorithm and random search algorithm, the paper considers simple hybrid genetic algorithm and hybrid random search algorithm. The objective is to analyze the performance of hybrid genetic algorithm and hybrid random search algorithm over other discussed algorithms for the classification problem. The experiments considered a feedforward NN trained with simple hybrid genetic algorithm/hybrid random search algorithm and 39 types of network structures and artificial data sets. In most cases, the hybrid evolutionary feedforward NNs seemed to be better than the other algorithms. We found few differences in the performance of the networks trained by applying the hybrid genetic algorithms, but found ample differences in the execution time. The results suggest that the hybrid evolutionary feedforward NN might be the best algorithm on the data sets we tested.