Autonomous ratio-memory cellular nonlinear network (ARMCNN) for pattern learning and recognition

Chung-Yu Wu*, Sn Ynng Tsai

*此作品的通信作者

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

A new type of CNN associative memory called the Autonomous ratio-memory Cellular Nonlinear Network (ARM-CNN) is proposed and analyzed. In the proposed ARMCNN, the input noisy patterns are sent into the cells as the initial cell state voltages. The proposed ARMCNN has the advantages of higher recognition rate (RR), higher number of learned and recognized patterns, and smaller signal ranges of cell state voltages. The RR of the ARMCNN is also modeled as the integration of the probability functions in the convergent regions of the phase plane plot of cell state voltages. Theoretical calculation results are consistent with simulation results.

原文English
主出版物標題Proceedings of the 2006 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2006
DOIs
出版狀態Published - 1 十二月 2006
事件2006 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2006 - Istanbul, Turkey
持續時間: 28 八月 200630 八月 2006

出版系列

名字Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

Conference

Conference2006 10th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2006
國家/地區Turkey
城市Istanbul
期間28/08/0630/08/06

指紋

深入研究「Autonomous ratio-memory cellular nonlinear network (ARMCNN) for pattern learning and recognition」主題。共同形成了獨特的指紋。

引用此