SetMju(newMju: Double);
newMju. Coefficient of inertia. The value is in the range [0.0; 1.0].
The SetMju method sets coefficient of inertia for learning of all the layers of the back-propagation network.
The inertia determines, which part of the delta value (calculated in the previous epoch of learning) to be used in the current epoch to correct synapse weights. If the user does not want to use the inertia, the newMju parameter should be set to zero.
The method use is given in the example for INeuralNetwork.LearnBack.
See also: