NeuNet Home Page
CorMac Home Page
NeuNet Home
Neural Nets
Screen Shots
Developer's Kit
Java Applets

Site Search
CorMac Home
VisiRex Home
Horse Racing

SFAM Neural Network
"Use for predicting classes"

[BackProp]      [SFAM]      [Combinations]

Training begins with just one hidden node whose weights are set equal to the first record and prediction is set equal to the class of the first record. Similarly, whenever a new class is encountered a new node is created. The node whose weights best match the current input supplies the prediction, provided the degree of match exceeds the vigilance threshold value. If this prediction is correct, the weights of this winning node are adjusted toward this input. If the prediction is wrong or vigilance threshold is not achieved, a new node is created with weights and prediction equal to this record.

CorMac Technologies Inc.
34 North Cumberland Street ~ Thunder Bay ON P7A 4L3 ~ Canada
E m a i l