The Design and Analysis of a CMOS Low-Power Large-Neighborhood CNN With Propagating Connections

The design of a large-neighborhood cellular nonlinear network (LN-CNN) with propagating connections is proposed. The propagating connections are utilized to achieve large-neighborhood templates in the shape of diamonds. Based on the propagating connections, each LN-CNN cell can only be connected to neighboring cells without interconnections to farther cells. Thus, it is suitable for very large scale integration implementation. The LN-CNN functions of diffusion, deblurring, and Muller-Lyer illusion are successfully verified. Meanwhile, the functions of erosion and dilation are expanded with the diamond-shaped LN templates. Furthermore, the simple N- and P-type synapses stop all the static current paths so that the dc power dissipation can be reduced to only 0.7 mW on standby and 18 mW in operation. An experimental LN-CNN chip with a 20 × 20 array has been fabricated using 0.18-mum CMOS technology. With the proposed LN-CNN chip, more applications and LN-CNN templates can be studied further.

[1]  Chung-Yu Wu,et al.  A new structure of large-neighborhood cellular nonlinear network (LN-CNN) , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[2]  Tamás Roska.  Analogic algorithms running on the CNN Universal Machine , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[3]  G. Linan,et al.  The CNNUC3: an analog I/O 64x64 CNN universal machine chip prototype with 7-bit analog accuracy , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[4]  K. Slot,et al.  Large-neighborhood templates implementation in discrete-time CNN Universal Machine with a nearest-neighbor connection pattern , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[5]  Ángel Rodríguez-Vázquez,et al.  ACE16k: the third generation of mixed-signal SIMD-CNN ACE chips toward VSoCs , 2004, IEEE Transactions on Circuits and Systems I: Regular Papers.

[6]  Tamás Roska,et al.  The CNN universal machine: an analogic array computer , 1993 .

[7]  Csaba Rekeczky,et al.  A real-time multitarget tracking system with robust multichannel CNN-UM algorithms , 2005, IEEE Transactions on Circuits and Systems I: Regular Papers.

[8]  Ángel Rodríguez-Vázquez,et al.  A 0.8-μm CMOS two-dimensional programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage , 1997, IEEE J. Solid State Circuits.

[9]  Ricardo Carmona-Galán,et al.  A CNN Universal Chip in CMOS Technology , 1996, Int. J. Circuit Theory Appl..

[10]  Chung-Yu Wu,et al.  The design of neuron-bipolar junction transistor (vBJT) cellular neural network (CNN) structure with multi-neighborhood-layer templates , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[11]  Tommaso Toffoli.  Cellular automata , 1998 .

[12]  A. Rodriguez-Vazquez,et al.  CNNUC3: a mixed-signal 64/spl times/64 CNN universal chip , 1999, Proceedings of the Seventh International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems.

[13]  Tommaso Toffoli,et al.  Cellular automata machines - a new environment for modeling , 1987, MIT Press series in scientific computation.

[14]  L. Chua.  Cnn: A Paradigm for Complexity , 1998 .

[15]  Franco Bagnoli,et al.  Cellular Automata , 2002, Lecture Notes in Computer Science.

[16]  Chung-Yu Wu,et al.  A new compact programmable /spl nu/BJT cellular neural network structure with adjustable neighborhood layers for image processing , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[17]  Chung-Yu Wu,et al.  The neuron-bipolar junction transistor (v-BJT)-a new device structure for VLSI neural network implementation , 1998, 1998 IEEE International Conference on Electronics, Circuits and Systems. Surfing the Waves of Science and Technology (Cat. No.98EX196).

[18]  L.O. Chua,et al.  Cellular neural networks , 1993, 1988., IEEE International Symposium on Circuits and Systems.

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

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

[21]  D. Cabello,et al.  On the emulation of large-neighborhood templates with binary CNN-based architectures , 2005, 2005 9th International Workshop on Cellular Neural Networks and Their Applications.

[22]  Chung-Yu Wu,et al.  A new compact neuron-bipolar cellular neural network structure with adjustable neighborhood layers and high integration level , 1999, ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349).

[23]  Chung-Yu Wu,et al.  A low power design on diffusive interconnection large-neighborhood cellular nonlinear network for giga-scale system application , 2004, Proceedings of the 2004 11th IEEE International Conference on Electronics, Circuits and Systems, 2004. ICECS 2004..

[24]  Chung-Yu Wu,et al.  A new compact neuron-bipolar junction transistor (/spl nu/BJT) cellular neural network (CNN) structure with programmable large neighborhood symmetric templates for image processing , 2001 .

[25]  Chin-Teng Lin,et al.  CNN-Based Hybrid-Order Texture Segregation as Early Vision Processing and Its Implementation on CNN-UM , 2007, IEEE Transactions on Circuits and Systems I: Regular Papers.