DocumentCode :
2970863
Title :
Implementation of pulse-coded neural networks
Author :
El-Leithy, N. ; Zaghloul, M. ; Newcomb, R.W.
Author_Institution :
Dept. of Electr. Eng., Maryland Univ., College Park, MD, USA
fYear :
1988
fDate :
7-9 Dec 1988
Firstpage :
334
Abstract :
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
Keywords :
MOS integrated circuits; encoding; hybrid computers; neural nets; MOS transistor threshold variation; coding; hysteresis; pulse-coded neural networks; semistate theory; Biological information theory; Educational institutions; Integrated circuit interconnections; Laboratories; MOS devices; MOSFETs; Neural networks; Neurons; Pulse modulation; Voltage;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Decision and Control, 1988., Proceedings of the 27th IEEE Conference on
Conference_Location :
Austin, TX
Type :
conf
DOI :
10.1109/CDC.1988.194323
Filename :
194323
Link To Document :
بازگشت