Improving recognition and generalization capability of back-propagation NN using a self-organized network inspired by immune algorithm (SONIA)

Authors:
Muhammad R. Widyanto;Hajime Nobuhara;Kazuhiko Kawamoto;Kaoru Hirota;Benyamin Kusumoputro
Affiliations:
Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, G3-49, 4259 Nagatsuta, Midori-ku, Yokohama 226-8502, Japan;Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, G3-49, 4259 Nagatsuta, Midori-ku, Yokohama 226-8502, Japan;Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, G3-49, 4259 Nagatsuta, Midori-ku, Yokohama 226-8502, Japan;Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, G3-49, 4259 Nagatsuta, Midori-ku, Yokohama 226-8502, Japan;Faculty of Computer Science, University of Indonesia, Depok Campus, West Java, Indonesia
Venue:
Applied Soft Computing
Year:
2005

Citing 7
Cited 4

The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network

Computer
Bayesian interpolation

Neural Computation
Developments and applications of the self-organizing map and related algorithms

Mathematics and Computers in Simulation - Special issue: signal processing and neural networks
Extending the Kohonen self-organizing map networks for clustering analysis

Computational Statistics & Data Analysis
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
On overfitting, generalization, and randomly expanded training sets

IEEE Transactions on Neural Networks
Using additive noise in back-propagation training

IEEE Transactions on Neural Networks

Prediction of first lactation 305-day milk yield in Karan Fries dairy cattle using ANN modeling

Applied Soft Computing
How Good Is the Backpropogation Neural Network Using a Self-Organised Network Inspired by Immune Algorithm (SONIA) When Used for Multi-step Financial Time Series Prediction?

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
BP neural networks combined with PLS applied to pattern recognition of Vis/NIRs

IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning
Neuro fuzzy and punctual kriging based filter for image restoration

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

To improve recognition and generalization capability of back-propagation neural networks (BP-NN), a hidden layer self-organization inspired by immune algorithm called SONIA, is proposed. B cell construction mechanism of immune algorithm inspires a creation of hidden units having local data recognition ability that improves recognition capability. B cell mutation mechanism inspires a creation of hidden units having diverse data representation characteristics that improves generalization capability. Experiments on a sinusoidal benchmark problem show that the approximation error of the proposed network is 1/17 times lower than that of BP-NN. Experiments on real time-temperature-based food quality prediction data shows that the recognition capability is 18% improved comparing to that of BP-NN. The development of the world first time-temperature-based food quality prediction demonstrates the real applicability of the proposed method in the field of food industry.