Abstract:
This article describes an automatic method for building of
distributed neural classifiers for pattern recognition. The
methodology is based upon the detection of reliable regions
in the representation space, i.e. clusters exclusively
composed of patterns from the same class. This detection is
performed using a hierarchical clustering method
associated with the supervised information provided by a
professor. The proposed methodology consists of
associating each of these regions with a Multi-Layer
Perceptron (MLP) which has to recognise elements inside
its region, while rejecting all others. Experimental results
for a real problem (handwritten digit recognition) reveal an
interesting generalisation behaviour of the distributed
classifier in comparison to the k-nearest neighbour
algorithm as well as a single MLP.