COMPETITIVE STOCHASTIC NEURAL NETWORKS FOR VECTOR QUANTIZATION OF IMAGES

Authors
GRANA M DANJOU A GONZALEZ AI ALBIZURI FX COTTRELL M
Citation
M. Grana et al., COMPETITIVE STOCHASTIC NEURAL NETWORKS FOR VECTOR QUANTIZATION OF IMAGES, Neurocomputing, 7(2), 1995, pp. 187-195
Citations number
20
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence",Neurosciences
Journal title
Neurocomputing → ACNP
ISSN journal
09252312
Volume
7
Issue
2
Year of publication
1995
Pages
187 - 195
Database
ISI
SICI code
0925-2312(1995)7:2<187:CSNNFV>2.0.ZU;2-I
Abstract
A stochastic approximation to the nearest neighbour (NN) classificatio n rule is proposed. This approximation is called Local Stochastic Comp etition (LSC). Some convergence properties of LSC are discussed, and e xperimental results are presented. The approach shows a great potentia l for speeding up the codification process, with an affordable loss of codification quality.