Information Processing Using a Model of Associative Memory

Abstract

Association mechanisms are considered to play Important roles in thinking in the human brain. Such mechanisms should be ana]ysed and utilized In machine intelligence in order to further work in the field. This paper describes a model of a neural network named 'Association', and considers its applications for Information processing. The Associatron stores a lot of entities in the same region of its structure, and recalls the whole of any entity from a part of it without any sequential search. From its structure, some properties are derived that are expected to be useful for humanlike information processing. Analysis of these properties is briefly described. An Associatron with i80 neurons has been simulated by a computer and has been applied to simple examples of concept formation and game playing. Hardware realization of an Associatron with 25 neurons made for trial purposes, is outlined, too.