SELECTION AND CONSOLIDATION OF MEMORIZED INFORMATION FOR DISTRIBUTED ASSOCIATIVE MEMORIES

Numerous studies have been made on the method of constructing the dist ributed-type associative memory. This paper discusses the method which selectively memorizes or memorizes by consolidation the information s tored in multiple associative memories in a new associative memory. In the distributed associative memory, the information (vector) to be st ored is memorized in a distributed way in the form of a matrix (called memorization matrix). Then, in general, it is difficult to know preci sely the original memorized information from the already constructed a ssociative memory. This paper proposes a method which can realize the selection and consolidation of the memorized information by constructi ng directly the memorization matrix of the new associative memory, usi ng the memorization matrices of the already constructed multiple assoc iative memories. The proposed method has the feature that it is not ne cessary to derive the information memories in each associative memory or to reconstruct the associative memory from the start using the memo rized information (relearning). It is a requirement which arises frequ ently in the construction, update and use of the associative memory to memorize selectively or in a consolidated form the information memori zed in multiple associative memories, in an associative memory. For su ch a purpose, the proposed method will be useful.