C++ Neural Networks and Fuzzy Logic: Preface

Special Features of the ART1 Model

One special feature of an ART1 model is that a two−thirds rule is necessary to determine the activity of

neurons in the F

1

 layer. There are three input sources to each neuron in layer F

1

. They are the external input,

the output of gain control, and the outputs of F

2

 layer neurons. The F

1

neurons will not fire unless at least two

of the three inputs are active. The gain control unit and the two−thirds rule together ensure proper response

from the input layer neurons. A second feature is that a vigilance parameter is used to determine the activity of

the reset unit, which is activated whenever there is no match found among existing patterns during

classification.