T. Kamio et H. Asai, Sparsely interconnected neural networks for associative memories applying discrete Walsh transform, IEICE T FUN, E82A(3), 1999, pp. 495-499
Citations number
8
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES
The conventional synthesis procedure of discrete time sparsely interconnect
ed neural networks (DTSINNs) for associative memories may generate the cell
s with only self-feedback due to the sparsely interconnected structure. Alt
hough this problem is solved by increasing the number of interconnections,
hardware implementation becomes very difficult. In this letter, we propose
the DTSINN system which stores the 2-dimensional discrete Walsh transforms
(DWTs) of memory patterns. As each element of DWT involves the information
of whole sample data, our system can associate the desired memory patterns,
which the conventional DTSINN fails to do.