Yin, H. and Allinson, N. M. (1997) Bayesian learning for selforganising maps. Electronic Letters, 33 (4). pp. 304305. ISSN 00135194
Full content URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumb...
Documents 

PDF
00583490.pdf  Whole Document Restricted to Repository staff only 278kB 
Item Type:  Article 

Item Status:  Live Archive 
Abstract
An extended selforganising learning scheme is proposed, namely the Bayesian selforganising map (BSOM), in which both the distance measure and neighbourhood function have been replaced by the neuron's `online' estimated posterior probabilities. Such posteriors, in a Bayesian inference sense, will then contribute to gradually sharpening the estimation for input distributions and model parameters for which generally there is little prior knowledge. The BSOM has been successfully used to team the underlying mixture distribution of input data, and hence form an optimal pattern classifier
Additional Information:  An extended selforganising learning scheme is proposed, namely the Bayesian selforganising map (BSOM), in which both the distance measure and neighbourhood function have been replaced by the neuron's `online' estimated posterior probabilities. Such posteriors, in a Bayesian inference sense, will then contribute to gradually sharpening the estimation for input distributions and model parameters for which generally there is little prior knowledge. The BSOM has been successfully used to team the underlying mixture distribution of input data, and hence form an optimal pattern classifier 

Keywords:  Bayes methods, artificial intelligence, pattern classification, probability, selforganising feature maps 
Subjects:  G Mathematical and Computer Sciences > G700 Artificial Intelligence 
Divisions:  College of Science > School of Computer Science 
ID Code:  5080 
Deposited On:  20 Apr 2012 17:32 
Repository Staff Only: item control page