From Data Topology to a Modular Classifier

TL;DR

This paper presents a modular neural classifier design using hierarchical clustering and multiple neural networks, improving recognition accuracy and robustness in handwritten digit classification.

Contribution

It introduces a novel hierarchical clustering method for defining reliable regions and combines multiple neural networks with a K-nearest neighbor classifier for enhanced modular classification.

Findings

Effective in handwritten digit recognition

Outperforms nonmodular classifiers

Demonstrates robustness and modularity

Abstract

This article describes an approach to designing a distributed and modular neural classifier. This approach introduces a new hierarchical clustering that enables one to determine reliable regions in the representation space by exploiting supervised information. A multilayer perceptron is then associated with each of these detected clusters and charged with recognizing elements of the associated cluster while rejecting all others. The obtained global classifier is comprised of a set of cooperating neural networks and completed by a K-nearest neighbor classifier charged with treating elements rejected by all the neural networks. Experimental results for the handwritten digit recognition problem and comparison with neural and statistical nonmodular classifiers are given.