# A novel associative memory model based on semi-tensor product (STP)

## TL;DR

This paper introduces a new associative memory model using the semi-tensor product to improve memory and association in intelligent systems.

## Contribution

A novel associative memory model using semi-tensor product is proposed, offering better accuracy with fewer nodes.

## Key findings

- The model uses STP to convert learning modes into algebraic forms for accurate memory storage.
- Algorithms are developed to update memory matrices and enhance association ability.
- Examples show the model outperforms DHNNs in accuracy with fewer nodes.

## Abstract

A good intelligent learning model is the key to complete recognition of scene information and accurate recognition of specific targets in intelligent unmanned system. This study proposes a new associative memory model based on the semi-tensor product (STP) of matrices, to address the problems of information storage capacity and association. First, some preliminaries are introduced to facilitate modeling, and the problem of information storage capacity in the application of discrete Hopfield neural network (DHNN) to associative memory is pointed out. Second, learning modes are equivalently converted into their algebraic forms by using STP. A memory matrix is constructed to accurately remember these learning modes. Furthermore, an algorithm for updating the memory matrix is developed to improve the association ability of the model. And another algorithm is provided to show how our model learns and associates. Finally, some examples are given to demonstrate the effectiveness and advantages of our results. Compared with mainstream DHNNs, our model can remember learning modes more accurately with fewer nodes.