A pulse stream system for low-power neuro-fuzzy computation

This paper describes a VLSI device designed for low-power Neuro-Fuzzy computation, which is based on Coherent Pulse Width Modulation. The device implements several Neural and Fuzzy paradigms. Weights are stored as a voltage on a pair of capacitors, which are sequentially refreshed by a built-in self-refresh circuit. The performance of the system is analyzed theoretically, and results are compared against values measured from a prototype device, which contains a 32/spl times/32 synaptic array, consuming 10 mW of power at 140 MCPS.

[1]  Hannu Tenhunen,et al.  Fully digital neural network implementation based on pulse density modulation , 1989, 1989 Proceedings of the IEEE Custom Integrated Circuits Conference.

[2]  Gabor C. Temes,et al.  Analog MOS integrated circuits , 1988 .

[3]  Marcello Chiaberge,et al.  A comparison between analog and pulse stream VLSI hardware for neural networks and fuzzy systems , 1994, Proceedings of the Fourth International Conference on Microelectronics for Neural Networks and Fuzzy Systems.

[4]  Michel Verleysen,et al.  An analog processor architecture for a neural network classifier , 1994, IEEE Micro.

[5]  L. M. Reyneri.  A performance analysis of pulse stream neural and fuzzy computing systems , 1995 .

[6]  Leonardo Maria Reyneri,et al.  Using Coherent Pulse Width And Edge Modulations In Artificial Neural Systems , 1993, Int. J. Neural Syst..

[7]  Alan F. Murray,et al.  Pulse-stream VLSI neural networks mixing analog and digital techniques , 1991, IEEE Trans. Neural Networks.

[8]  Alan F. Murray,et al.  Integrated pulse stream neural networks: results, issues, and pointers , 1992, IEEE Trans. Neural Networks.

[9]  Marcello Chiaberge,et al.  CINTIA: a neuro-fuzzy real time controller for low power embedded systems , 1994, Proceedings of the Fourth International Conference on Microelectronics for Neural Networks and Fuzzy Systems.

[10]  Dante Del Corso.  Hardware Implementations of Artificial Neural Networks , 1993, IWANN.