An associative memory model with very high memory rate: Image storage by sequential addition learning

TL;DR

This paper introduces a neural network model capable of high-capacity, bidirectional associative memory with near-perfect memory rate, capable of recalling multiple patterns simultaneously and learning new patterns without disrupting existing ones.

Contribution

The proposed model achieves a memory rate close to 100% and allows for simultaneous pattern recall and incremental learning, which is a significant advancement over previous associative memory models.

Findings

Memory rate of 0.987 achieved

Can recall multiple patterns simultaneously

Supports additional learning without disrupting stored patterns

Abstract

In this paper, we present a neural network system related to about memory and recall that consists of one neuron group (the "cue ball") and a one-layer neural net (the "recall net"). This system realizes the bidirectional memorization learning between one cue neuron in the cue ball and the neurons in the recall net. It can memorize many patterns and recall these patterns or those that are similar at any time. Furthermore, the patterns are recalled at most the same time. This model's recall situation seems to resemble human recall of a variety of similar things almost simultaneously when one thing is recalled. It is also possible for additional learning to occur in the system without affecting the patterns memorized in advance. Moreover, the memory rate (the number of memorized patterns / the total number of neurons) is close to 100%; this system's rate is 0.987. Finally, pattern data constraints become an important aspect of this system.