A neural network chip using CPWM modulation
This paper describes a silicon implementation of an Artificial Neural Networks based on Coherent Pulse Width modulation techniques. Synapses use current generators controlled by an input Pulse Stream. Net charge generated is the product of synaptic current by pulse width. Neurons accumulate synaptic contributions and convert internal activation into an output Pulse Stream. A system optimized for lowest computation energy and highest reconfigurability has been designed, manufactured and tested.
Unable to display preview. Download preview PDF.
- A. F. Murray, D. Del Corso, and L. Tarassenko, “Pulse-Stream VLSI Neural Networks Mixing Analog and Digital Techniques”, IEEE Trans. on Neural Networks, vol. 2, no. 2, March 1991, pp. 193–204.Google Scholar
- P.D. Wasserman, “Neural Computing: Theory and Practice”, Now York, Van Noslrand Reinhold, 1989.Google Scholar
- A. Hamilton, A.F. Murray, D.J. Baxter, S. Churcher, H.M. Reekie, and L. Tarassenko, “Integrated Pulse Stream Neural Networks: Results, Issues and Pointers”, IEEE Trans. on Neural Networks, vol. 3, May 1992, pp. 404–413.Google Scholar
- L.M. Reyneri, “Silicon Implementations of Artificial Neural Systems Based on Pulse Stream Modulations”, Final Report of NERVES EEC Project, E-BRA 3049, July 1991.Google Scholar
- H.P. Graf, E. Sackinger, B. Boser, and L.D. Jackell, “Recent Developments of Electronic Neural Nets in the USA and Canada”, Proc. Int'l Conf. on Microelectronics for Neural Networks, Munich, October 1991, pp. 471–490.Google Scholar
- L.M. Reyneri, “A Performance Analysis of Pulse Stream Neural Networks”, submitted to IEEE Trans. on Neural Networks, Oct. 1992.Google Scholar