A learnable self-feedback ratio-memory cellular nonlinear network (SRMCNN) for associative memory applications

Jui Lin Lai*, Chung-Yu Wu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

A self-feedback ratio-memory cellular nonlinear network (SRMCNN) with the B template and the modified Hebbian learning algorithm to learn and recognize the image patterns is proposed and analyzed. In the proposed SRMCNN, the coefficients of space-variant B templates are determined from the exemplar patterns during the learning period. The weights are the ratio of the absolute summation of its neighborhood weights in the B templates was stored in the associative memory. This SRMCNN can recognize the learned patterns with distinct white-black noise and output the correct patterns. The Matlab and HSPICE software has been simulated the operation of the proposed SRMCNN. It is shown that the 18×18 SRMCNN can successfully learned and recognized 8 incompletely noisy patterns. As compared to other learnable CNN as associate memories, the proposed SRMCNN could improve pattern learning and recognition capability. The architecture can be implemented in nano-CMOS technology for giga-scale learning system in the real-time applications.

Original languageEnglish
Title of host publication11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004
Pages183-186
Number of pages4
DOIs
StatePublished - 1 Dec 2004
Event11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004 - Tel Aviv, Israel
Duration: 13 Dec 200415 Dec 2004

Publication series

Name11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004

Conference

Conference11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004
CountryIsrael
CityTel Aviv
Period13/12/0415/12/04

Fingerprint Dive into the research topics of 'A learnable self-feedback ratio-memory cellular nonlinear network (SRMCNN) for associative memory applications'. Together they form a unique fingerprint.

Cite this