InitSynapses(MaxAbsoluteValue: Double; layerIndex: Integer);
MaxAbsoluteValue. Maximum value of the synapse weight.
layerIndex. Layer index.
The InitSynapses method sets values of synapse weights for the specified layer according to the set parameters.
InitSynapses generates values for synapses of all the neurons of the specified layer. Indexation of the layers is continuous and starts with zero.
The following methods can also be used to set values of synapse weights:
As an example a function is given, which input has neural network fed into (the Net parameter), as well as the logical parameter Layer that defines the method of weights generation. If Layer is set to True, values of synapse weights for different layers are generated by using different methods. If Layer is set to False, all the weights are generated by one method.
To execute the example, add a link to the NN system assembly.
Function m_InitSynapses(Net: NeuralNetwork; Layer: Boolean): NeuralNetwork;
Var
lCount, i: Integer;
Begin
If Layer Then
// initialize synapses by different methods
lCount := Net.GetNumberOfLayers;
For i := 0 To lCount - 1 Do
net.InitSynapsesConvexEx(i);
End For;
Net.InitSynapses(0.9, lCount - 1);
Else
// initialize all the synapses by one method
Net.InitSynapsesConvex;
End If;
Return Net;
End Function m_InitSynapses;
After executing the example the values of synapse weights are generated by the selected method.
See also: