Cellular Neural Networks: an Approach to Circuit Design and Information Processing

Cellular Neural Networks are arrays of simple nonlinear dynamical systems in which each cell is connected to its nearest neighbors only, which makes them particularly well-suited for VLSI implementations. To highlight this key point, the design of a low power 1.5 μm CMOS CNN architecture is reported, which correctly operates within a wide range of power supply voltages. The proposed circuit is useful because it can operate at low voltages whenever allowed by operating speed requirements and at larger voltage (and power consumption) whenever speed constraints prevail. CNNs applications mainly lie in image preprocessing tasks, for which it is essential to understand how the information (an image), introduced as initial condition, propagates in the network. Two different and somehow opposite behaviors are possible, namely local diffusion between neighboring cells only, or global propagation through the entire lattice. Some practical consequences of this mode of operation are also reported from [5, 6]

[1]  Leon O. Chua,et al.  Pattern formation properties of autonomous Cellular Neural Networks , 1995 .

[2]  Josef A. Nossek.  DESIGN AND LEARNING WITH CELLULAR NEURAL NETWORKS , 1996 .

[3]  S. Graffi,et al.  CMOS implementation of an analogically programmable cellular neural network , 1993 .

[4]  Leon O. Chua,et al.  CNN cloning template: hole-filler , 1990 .

[5]  Leon O. Chua,et al.  CNN cloning template: shadow detector , 1990 .

[6]  Leon O. Chua,et al.  A CNN handwritten character recognizer , 1992, Int. J. Circuit Theory Appl..

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

[8]  P. Thiran,et al.  An approach to information propagation in 1-D cellular neural networks. II. Global propagation , 1998 .

[9]  Patrick Thiran,et al.  An approach to information propagation in cellular neural networks - Part I : Local diffusion , 1998 .

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

[11]  Ángel Rodríguez-Vázquez,et al.  A VLSI-oriented continuous-time CNN model , 1996 .

[12]  Á. Rodríguez-Vázquez,et al.  Current-mode techniques for the implementation of continuous- and discrete-time cellular neural networks , 1993 .

[13]  Patrick Thiran,et al.  An approach to information propagation in 1-dimensional cellular neural networks - Part II : global propagation , 1998 .

[14]  Leon O. Chua,et al.  CNN cloning template: connected component detector , 1990 .

[15]  L. Chua,et al.  An analytic method for designing simple cellular neural networks , 1991 .