Paper on self-organizing topographic networks for classification

[Jim Williamson]

I would like to announce the availability of a new paper, 
accepted for publication in Neural Computation. 

Available at: http://cns-web.bu.edu/pub/jrw/www/pubs.html

------------------------------------------------------------

        SELF-ORGANIZATION OF TOPOGRAPHIC MIXTURE NETWORKS
                USING ATTENTIONAL FEEDBACK

                James R. Williamson
        Department of Cognitive and Neural Systems
        Boston University,  Boston, MA 02215

              Neural Computation, in press.

                        ABSTRACT
This paper proposes a neural network model of supervised learning
which employs biologically-motivated constraints of using local,
on-line, constructive learning.  The model possesses two novel
learning mechanisms.  The first is a network for learning topographic
mixtures.  The network's internal category nodes are the mixture
components, which learn to encode smooth distributions in the input
space by taking advantage of topography in the input feature maps.  
The second mechanism is an attentional biasing feedback circuit.  
When the network makes an incorrect output prediction, this feedback
circuit modulates the learning rates of the category nodes, by 
amounts based on the sharpness of their tuning, in order to improve 
the network's prediction accuracy.  The network is evaluated on 
several standard classification benchmarks and shown to perform well
in comparison to other classifiers.