Class-wise Classifier Design Capable of Continual Learning using Adaptive Resonance Theory-based Topological Clustering

TL;DR

This paper introduces a supervised classification algorithm that leverages ART-based topological clustering for continual learning, enabling the model to adapt to new classes without forgetting previous ones.

Contribution

It presents a novel class-wise classifier that uses ART-based clustering for continual learning, which is theoretically capable of incremental learning for each class.

Findings

Superior classification performance over existing continual learning algorithms

Effective handling of new classes through separate ART-based clustering

Demonstrated continual learning capability in simulations

Abstract

This paper proposes a supervised classification algorithm capable of continual learning by utilizing an Adaptive Resonance Theory (ART)-based growing self-organizing clustering algorithm. The ART-based clustering algorithm is theoretically capable of continual learning, and the proposed algorithm independently applies it to each class of training data for generating classifiers. Whenever an additional training data set from a new class is given, a new ART-based clustering will be defined in a different learning space. Thanks to the above-mentioned features, the proposed algorithm realizes continual learning capability. Simulation experiments showed that the proposed algorithm has superior classification performance compared with state-of-the-art clustering-based classification algorithms capable of continual learning.