Associatron-A Model of Associative Memory

Abstract

Thinking in the human brain greatly depends upon association mechanisms which can be utilized in machine intelligence. An associative memory device, called " Associatron," is proposed. The Associatron stores entities represented by bit patterns in a distributed manner and recalls the whole of any entity from a part of it. If the part is large, the recalled entity will be accurate; on the other hand, if the part is small, the recalled entity will be rather ambiguous. Any number of entities can be stored, but the accuracy of the recalled entity decreases as the number of entities increases. The Associatron is considered to be a simplified model of the neural network and can be constructed as a cellular structure, where each cell is connected to only its neighbor cells and all cells run in parallel. From its mechanisms some properties are derived that are expected to be utilized for human-like information processing. After these properties have been analyzed, an Associatron which deals with entities composed of less than 180 bits is simulated by a computer. Simple examples of its applications for concept formation and game playing are presented and the thinking process by the sequence of associations is described.