Kohonen feature map associative memory with area representation for sequential analog patterns

In this paper, we propose a Kohonen feature map associative memory with area representation for sequential analog patterns. This model is based on the Kohonen feature map associative memory with area representation for sequential patterns. Although the conventional Kohonen feature map associative memory with area representation for sequential patterns can deal with only binary (bipolar) patterns, the proposed model can deal not only binary (bipolar) patterns but also analog patterns. The proposed model can learn sequential analog patterns successively, and has robustness for damaged neurons. We carried out a series of computer experiments and confirmed that the effectiveness of the proposed model.