This class implements the weights of a neural network, i.e. a weighted link. It propagates changes to connected neurons, so that they can recalculate their outputs when necessary (and only then). Moreover, each weight can calculate its gradient component, provided that the output neurons have had their 'delta' set.
from()neuron times the weight value.
NeuralNetclass for use.
double set(double x)
virtual ostream &writeTo(ostream &o)
istream &readFrom(istream &i)
static istream& dummyRead(istream &i)