Abstract
The paper reports the possibilities of the neural network simulation using SPICE models. In the design and testing of the experimental neural networks it is very useful to tray the behavior of neural network in many reel conditions. SPICE can provide the initial training sets and also assist in network development, both at the circuit level and the theoretical level.
Cuvinte cheie
neural network
perceptron
simulation
back propagation algorithm
axon
cell
adaptive network