Implementation of pulse-coded neural networks
N. El-Leithy, Mona Elwakkad Zaghloul, R.W. Newcomb · 2003
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.>