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)
Embedded self-adaptation to escape from local optima
Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
Hi-index | 0.00 |
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.