Variable-sized Fast Kohonen Feature Map Associative Memory using Area Representation for Sequential Patterns

In this paper, we propose a Variable-sized Fast Kohonen Feature Map Associative Memory using Area Representation for Sequential Patterns (VFKFMAM-AR-SP). This model is based on the conventional Fast Kohonen Feature Map Associative Memory using Area Representation for Sequential Analog Patterns (FKFMAM-AR-SAP) and Variable-sized Kohonen Feature Map Associative Memory with Refractoriness based on Area Representation (VKFMAM-R-AR). In the proposed model, the connection weight fixed and semi-fixed neurons are introduced, and the pattern that has already been learned is not destroyed and a new pattern can be memorized. Moreover, when unknown patterns are given, neurons can be added in the map layer if necessary. We carried out a series of computer experiments and confirmed the effectiveness of the proposed model.