In this paper, we propose a Self-Organizing Map-based Probabilistic Associative Memory
(SOMPAM). The proposed SOMPAM is based on Self-Organizing Map and it is composed of
the Input/Output Layer and the Map Layer. In this model, stored pattern sets are memorized
with its own brief degree, and probabilistic associations based on brief degree for analog
pattern sets including one-to-many relations can be realized. And it can also realize
additional learning. We carried out a series of computer experiments and confirmed that the …

In this paper, we propose a Self-Organizing Map-based Probabilistic Associative Memory for
Sequential Patterns (SOMPAM-SP). The proposed model is based on Self-Organizing Map
and it has an Input/Output Layer and a Map Layer. The Input/Output Layer is divided into
three parts;(1) Input Part,(2) Output Part and (3) Brief Degree Part. In this model, stored
pattern sequences are divided into pattern sets composed of two patterns (the pattern at the
time t and the pattern at the time t+ 1) and each set is memorized with its own brief degree. In …