Bidirectional Associative Memories, Self-Organizing Maps and k-Winners-Take-All: Uniting feature extraction and topological principles

摘要

In this paper, we introduce a network combining k-Winners-Take-All and Self-Organizing Map principles within a Feature Extracting Bidirectional Associative Memory. When compared with its ldquostrictly winner-take-allrdquo version, the modified model shows increased performance for clustering, by producing a better weight distribution and a lower dispersion level (higher density) for each given category. Moreover, because the model is recurrent, it is able to develop prototype representations strictly from exemplar encounters. Finally, just like any recurrent associative memory, the model keeps its reconstructive memory and noise filtering properties.