Programmable non-linearity for STAR cellular neural networks

The implementation of a feasible circuital solution for modeling complex systems as STAR Cellular Neural Networks requires circuits with features and performances tailored for the specific application. In particular, this paper deals with the design of a current mode digitally programmable non-linearity that has been properly developed for a “time-division architecture” implementation of a first order STAR CNN system.

[1]  Masahiko Yoshimoto,et al.  An image sensor with fast objects' position extraction function , 2003 .

[2]  J. Ramirez-Angulo,et al.  Analog VLSI weighted median filters , 2000, Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems (Cat.No.CH37144).

[3]  P. Szolgay,et al.  Analog combinatorics and cellular automata-key algorithms and layout design , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[4]  Leon O. Chua,et al.  Star Cellular Neural Networks for Associative and Dynamic Memories , 2004, Int. J. Bifurc. Chaos.

[5]  Wouter A. Serdijn,et al.  Analog wavelet transform employing dynamic translinear circuits for cardiac signal characterization , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[6]  Alejandro Díaz-Sánchez,et al.  A fully parallel CMOS analog median filter , 2004, IEEE Transactions on Circuits and Systems II: Express Briefs.

[7]  Jerry M. Mendel,et al.  The hysteretic Hopfield neural network , 2000, IEEE Trans. Neural Networks Learn. Syst..

[8]  V. Bonaiuto,et al.  Multiplexed Circuit for Star-CNN Architecture , 2006, 2006 10th International Workshop on Cellular Neural Networks and Their Applications.

[9]  S. Summerfield.  Simple multiplexer circuit for CMOS VLSI , 1990 .

[10]  K. Urahama,et al.  Direct analog rank filtering , 1995 .