SetSigmoidAlpha(newAlphaValue: Double);
SetSigmoidAlpha(newAlphaValue: double);
newAlphaValue. Value of the Alpha coefficient.
The SetSigmoidAlpha method sets value of the Alpha coefficient for the sigmoid functions of signal propagation in the network.
To execute the SetSigmoidAlpha method, all the neurons in the network should use one and the same function of signal propagation in the network.
The function of signal propagation in the network is specified on creating a network by the INeuralNetwork.CreateNetworkEx method. The following methods are used to change the type of function: INeuralNetwork.SetSigmoidFuncs and INeuralNetwork.SetSigmoidFuncsEx.
As an example, a function is given, which input has a neural network fed into (the Net parameter). To execute the example, add a link to the NN system assembly.
Function m_SetSigmoidAlpha(Net: NeuralNetwork): NeuralNetwork;
Begin
Net.SetSigmoidFuncs(4);
Net.SetSigmoidAlpha(0.25);
Return Net;
End Function m_SetSigmoidAlpha;
After executing the example an exponential sigmoid function is used and the Alpha coefficient is determined for all the neurons of the network.
As an example, a function is given, which input has a neural network fed into (the Net parameter).
Public Shared Function m_SetSigmoidAlpha(Net: NeuralNetwork): NeuralNetwork;
Begin
Net.SetSigmoidFuncs(4);
Net.SetSigmoidAlpha(0.25);
Return Net;
End Function;
After executing the example an exponential sigmoid function is used and the Alpha coefficient is determined for all the neurons of the network.
See also: