Implementation of pulse-coded neural networks

The philosophy of pulse-coded neural-type networks is reviewed, and some MOS circuits for their implementation are given. A means of obtaining the coding through hysteresis and a means of adjusting weights through MOS transistor threshold variation are discussed. Semistate theory is suggested as an ideal theoretical tool for neural network studies.<<ETX>>

[1]  Robert W. Newcomb,et al.  Some circuits and systems applications of semistate theory , 1989 .

[2]  N. El-Leithy,et al.  Hysteresis in neural-type circuits , 1988, 1988., IEEE International Symposium on Circuits and Systems.

[3]  William Francis Ganong,et al.  Review of Medical Physiology , 1969 .

[4]  Hewitt D. Crane,et al.  Neuristor-A Novel Device and System Concept , 1962, Proceedings of the IRE.

[5]  Alan F. Murray,et al.  Asynchronous VLSI neural networks using pulse-stream arithmetic , 1988 .

[6]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[7]  S. Yoshizawa,et al.  An Active Pulse Transmission Line Simulating Nerve Axon , 1962, Proceedings of the IRE.