Adaptive Resonance Theory-based Topological Clustering with a Divisive Hierarchical Structure Capable of Continual Learning. (arXiv:2201.10713v1 [cs.LG])

Web: http://arxiv.org/abs/2201.10713

Thanks to an ability for handling the plasticity-stability dilemma, Adaptive
Resonance Theory (ART) is considered as an effective approach for realizing
continual learning. In general, however, the clustering performance of
ART-based algorithms strongly depends on a similarity threshold, i.e., a
vigilance parameter, which is data-dependent and specified by hand. This paper
proposes an ART-based topological clustering algorithm with a mechanism that
automatically estimates a similarity threshold from a distribution of data
points. In addition, for the improving information extraction performance, …

arxiv clustering learning theory