Kohonen Feature Map Probabilistic Associative Memory based on Weights Distribution

M. Koike and Y. Osana (Japan)

Keywords

Kohonen Feature Map (Self-Organizing Map), Associative Memory, Probabilistic Association, Successive Learning, Area Representation

Abstract

In this paper, we propose a Kohonen Feature Map Probabilistic Associative Memory based on Weights Distribution. This model is based on the conventional Kohonen Feature Map Associative Memory with Area Representation. The proposed model can realize probabilistic association for the training set including one-to-many relations. Moreover, this model has enough robustness for noisy input and damaged neurons. We carried out a series of computer experiments and conīŦrmed the effectiveness of the proposed model.

Important Links:



Go Back