AUTHOR=Hou Yanfang , Tian Hui , Wang Chengmao 

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

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2024.1384924

DOI=10.3389/fncom.2024.1384924

ISSN=1662-5188

ABSTRACT=This paper proposes a new associative memory model based on the semi-tensor product of matrices (STP) to address the problems of information storage capacity and association.Firstly, learning modes are equivalently converted into their algebraic forms by using STP. And a memory matrix is constructed to accurately remember these learning modes. Secondly, an algorithm for updating the memory matrix is developed to improve the association ability of the model. Furthermore, another algorithm is provided to show how our model learns and associates.Compared with mainstream discrete Hopfield neural networks, our model can remember learning modes more accurately with fewer nodes. Finally, some examples are given to demonstrate the effectiveness and advantages of our results.