SASEGASA: an evolutionary algorithm for retarding premature convergence by self-adaptive selection pressure steering

Authors:
Michael Affenzeller;Stefan Wagner
Affiliations:
Institute of Systems Science, Systems Theory and Information Technology, Johannes Kepler University, Linz, Austria;Institute of Systems Science, Systems Theory and Information Technology, Johannes Kepler University, Linz, Austria
Venue:
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
Year:
2003

Citing 3
Cited 2

A massively parallel architecture for a self-organizing neural pattern recognition machine

Computer Vision, Graphics, and Image Processing
Fundamentals of Artificial Neural Networks

Fundamentals of Artificial Neural Networks
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)

SASEGASA: A New Generic Parallel Evolutionary Algorithm for Achieving Highest Quality Results

Journal of Heuristics
Embedded self-adaptation to escape from local optima

Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a competitive neural network with binary synaptic weights is proposed. The aim of this network is to cluster or categorize binary input data. The neural network uses a learning mechanism based on activity levels that generates new binary synaptic weights that evolve toward medianoids of the clusters or categorizes that are being formed by the process units of the network, since the medianoid is the better representation of a cluster for binary data when the Hamming distance is used. The proposed model has been applied to codebook generation in vector quantization (VQ) for binary fingerprint image compression. The binary neural network find a set of representative vectors (codebook) for a given training set minimizing the average distortion.