Summary
International Symposium on Nonlinear Theory and its Applications
2010
Session Number:A3L-D
Session:
Number:A3L-D2
Kohonen Feature Map Probabilistic Associative Memory based on Weights Distribution and Area Neuron Increase and Decrease
Takahiro HADA, Yuko OSANA,
pp.181-184
Publication Date:2010/9/5
Online ISSN:2188-5079
Summary:
In this paper, we propose a Kohonen Feature Map Probabilistic Associative Memory based on Weights Distribution and Area Neuron Increase and Decrease. This model is based on the conventional Kohonen Feature Map Probabilistic Associative Memory based on Weights Distribution. In the proposed model, the winner neuron is selected from the neurons in the Map Layer whose connection weights are similar to the input pattern, and the associations based on weights distribution are realized. Moreover, the weight distribution in the Map Layer can be modified by the increase and decrease of neurons in each area. This model has enough robustness for noisy input and damaged neurons. We carried out a series of computer experiments and confirmed the eｆｆectiveness of the proposed model.