The design of ratio-memory cellular neural network (RMCNN) with self-feedback template weight for pattern learning and recognition
Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications - Trang 609-615
Tóm tắt
In this paper, a new type of the ratio-memory cellular neural network (RMCNN) with spatial-dependent self-feedback A-template weights is proposed and designed to recognize and classify the black-white image patterns. In the proposed RMCNN, the combined four-quadrant multiplier and two-quadrant divider with separated magnitude and sign is used to implement the Hebbian learning function and the ratio memory. To enhance the capability of pattern learning and recognition from noisy input patterns, the Z-template and the spatial-dependent self-feedback weights in the template A are applied to the proposed new type of RMCNN. The pattern learning and recognition function of the 18/spl times/18 RMCNN is simulated by Matlab software. It has been verified that the advanced RMCNN has the advantages of more stored patterns for recognition, and better recovery rate as compared to the original RMCNN. Thus the proposed RMCNN has great potential in the applications of neural associate memory for image processing.
Từ khóa
#Cellular neural networks #Pattern recognition #Capacitors #Leakage current #Neurofeedback #Neural networks #Feedforward neural networks #Image processing #Image recognition #CouncilsTài liệu tham khảo
10.1109/MWSCAS.1994.519298
10.1109/ISCAS.1994.409632
wu, 1997, The Design of CMOS modified Hopfield Neural Network for pattern Recognition, Proc Int Symp Multimedia Information, 585
10.1109/ICSMC.1997.626223
wu, 2000, The Design of Cellular Neural Network with Ratio Memory for Pattern Learning and Recognition, 6th IEEE International Workshop on Cellular Neural Network and Their Application CNNA 2000, 301
10.1109/CNNA.1996.566486
lan, 1995, CMOS current-mode outstar neural networks with long-period analog ratio memory, Proc 1995 Int Symp on Circuits and Syst, iii, 1676
wu, 1996, CMOS current-mode neural associative memory design with on-chip learning, IEEE Trans Neural Networks, 7, 167, 10.1109/72.478401
10.1109/82.219843
lan, 1995, Analog CMOS current-mode implementation of the feedforward neural network with on-chip learning and storage, 1995 Int Conf Neural Networks
10.1109/ISCAS.1988.15089