The design of CMOS nonself-feedback ratio memory cellular nonlinear network without elapsed operation for pattern learning and recognition

In this paper, a nonself-feedback ratio memory cellular nonlinear network (RMCNN) without elapsed operation is proposed and implemented in CMOS for image pattern learning and recognition. In the non-self-feedback RMCNN, the self-feedback template coefficient is not used and operation of non-self-feedback RMCNN can be simplified. The final weights of template A are generated directly after learning by incorporating the ratio-memory function into the learning rule so that no elapsed period is required for ratio memory. In the proposed RMCNN, simple multiplication circuit and comparator circuit are used and the chip area can be reduced. The pattern learning and recognition behavior of the proposed RMCNN is simulated by Matlab and Hspice. It is found that the performance is the same as that of RMCNN with elapsed operation.

[1]  T. Roska.  Analog events and a dual computing structure using analog and digital circuits and operators , 1988 .

[2]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[3]  Péter Szolgay,et al.  A fast fixed point learning method to implement associative memory on CNNs , 1997 .

[4]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[5]  M. Brucoli,et al.  An approach to the design of space-varying cellular neural networks for associative memories , 1994, Proceedings of 1994 37th Midwest Symposium on Circuits and Systems.

[6]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[7]  Chung-Yu Wu,et al.  The design of cellular neural network with ratio memory for pattern learning and recognition , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[8]  Zhong Zhang,et al.  On the associative memories in cellular neural networks , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[9]  Leon O. Chua,et al.  Autonomous cellular neural networks: a unified paradigm for pattern formation and active wave propagation , 1995 .

[10]  Giovanni Costantini,et al.  Multiplierless digital learning algorithm for cellular neural networks , 2001 .

[11]  Chung-Yu Wu,et al.  A learnable cellular neural network structure with ratio memory for image processing , 2002 .

[12]  Kari Halonen,et al.  CMOS implementation of associative memory using cellular neural network having adjustable template coefficients , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

[13]  Chung-Yu Wu,et al.  CMOS current-mode outstar neural networks with long-period analog ratio memory , 1995, Proceedings of ISCAS'95 - International Symposium on Circuits and Systems.

[14]  Chung-Yu Wu,et al.  CMOS current-mode neural associative memory design with on-chip learning , 1996, IEEE Trans. Neural Networks.

[15]  S. Grossberg.  Nonlinear difference-differential equations in prediction and learning theory. , 1967, Proceedings of the National Academy of Sciences of the United States of America.

[16]  A. Lukianiuk.  Capacity of cellular neural networks as associative memories , 1996, 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96).

[17]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .