Im working on artificial neural networks (specifically SOM) in the context of data fault detection and diagnosis.
I only consider two classes in my application : faulty data and correct data.
My data are temperature values during a whole day.
I built my network upon 64 neurons, the training is absolutely perfect!
the problem resides in classifying these 64 neurons into two classes.
I cant find a criterion to do that.
Does anyone have an idea about this kind of neural networks application??
I'll be thankful for any help.