The design of cellular neural network with ratio memory for pattern learning and recognition

Wu, Chung‐Yu; Cheng, Chiu-Hung

doi:10.1109/cnna.2000.876862

Cited by 11 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a nonlinear analog processor with local interconnect and dual-value output, the cellular neural network (CNN) proposed by Chua et al in 1988 is particularly suitable for the implementation of large-scale circuits [1,2]. The results of CNN research have been widely used in many fields such as biomedicine [3], automatic control [4], pattern recognition [5], signal processing [6], and secure communication [7]. In particular, CNNs are the most extensively used in image processing including noise reduction, edge detection, and character recognition [8−10].…”

Section: Introductionmentioning

confidence: 99%

Integrating dual-role variables in data envelopment analysis

Yang

Liang

et al. 2010

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

Memristor with memory properties can be applied to connection points (synapses) between cells in a cellular neural network (CNN). This paper highlights memristor crossbar-based multilayer CNN (MCM-CNN) and its application to edge detection. An MCM-CNN is designed by adopting a memristor crossbar composed of a pair of memristors. MCM-CNN based on the memristor crossbar with changeable weight is suitable for edge detection of a binary image and a color image considering its characteristics of programmablization and compactation. Figure of merit (FOM) is introduced to evaluate the proposed structure and several traditional edge detection operators for edge detection results. Experiment results show that the FOM of MCM-CNN is three times more than that of the traditional edge detection operators.

show abstract

Section: Introductionmentioning

confidence: 99%

Integrating dual-role variables in data envelopment analysis

Yang

Liang

et al. 2010

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

show abstract

The design of ratio-memory cellular neural network (RMCNN) with self-feedback template weight for pattern learning and recognition

Cheng

Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications

View full text Add to dashboard Cite

In lhis paper. a new type of the ratio-memory cellular neural network W C N N ) with spatialdependent self-feedback A-template weights is proposed and designed to recogni2e and classify the black-white image pattems. In the proposed RMCNN. the combined fourquadrant multiplier and lwo-quadrant divider wilh repmed m@tude and sign is used 10 implement the Hebbien l d g hulaion and the ratio memory. To enhance the capability of pmem le-g and recognition from noisy input pattems, the 2-template and the spatialdependent self-feedback weighlr in the lemplate A are applied to the proposed new typc of RMCNN. The pattm l d n g and recognition fundion of the 18x18 RMCNN is simulated by Matlab soflware. If has been verified lhat the advanced RMCNN has the advantages of more stored panems for recognition. and better recovery rate as compared lo the original RMCNN. Thus the pmpased RMCNN has great potential in the applications of neural associate memory for image pracessing.

show abstract

Non-saturated binary image learning and recognition using the ratio-memory cellular neural network (RMCNN)

Hsieh²,

Chen³

et al.

Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications

View full text Add to dashboard Cite

The design of cellular neural network with ratio memory for pattern learning and recognition

Cited by 11 publications

References 10 publications

Integrating dual-role variables in data envelopment analysis

Integrating dual-role variables in data envelopment analysis

The design of ratio-memory cellular neural network (RMCNN) with self-feedback template weight for pattern learning and recognition

Non-saturated binary image learning and recognition using the ratio-memory cellular neural network (RMCNN)

Contact Info

Product

Resources

About