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

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.

arXiv commentThis paper is currently under review. arXiv admin note: substantial text overlap with arXiv:2201.10713

References in corpus (6)

• Overcoming catastrophic forgetting in neural networks
• Continual Learning Through Synaptic Intelligence
• A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks
• Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization
• Adaptive Resonance Theory-based Topological Clustering with a Divisive Hierarchical Structure Capable of Continual Learning
• Continual Learning in Predictive Autoscaling

Cited by in corpus (1)

• Reference Vector Adaptation and Mating Selection Strategy via Adaptive Resonance Theory-based Clustering for Many-objective Optimization