Method | Description | |
---|---|---|
Compute ( INeuralData input, NeuralOutputHolder useHolder ) : INeuralData |
Compute the output for a given input to the neural network. This method provides a parameter to specify an output holder to use. This holder allows propagation training to track the output from each layer. If you do not need this holder pass null, or use the other compare method.
|
|
Init ( BasicNetwork network ) : void |
Setup the network logic, read parameters from the network.
|
|
PreprocessLayer ( ILayer layer, INeuralData input, ISynapse source ) : void |
Can be overridden by subclasses. Usually used to implement recurrent layers.
|
Method | Description | |
---|---|---|
Compute ( NeuralOutputHolder holder, ILayer layer, INeuralData input, ISynapse source ) : void |
Internal computation method for a single layer. This is called, as the neural network processes.
|
public Compute ( INeuralData input, NeuralOutputHolder useHolder ) : INeuralData | ||
input | INeuralData | The input provide to the neural network. |
useHolder | NeuralOutputHolder | Allows a holder to be specified, this allows /// propagation training to check the output of each layer. |
return | INeuralData |
public Init ( BasicNetwork network ) : void | ||
network | BasicNetwork | The network that this logic class belongs to. |
return | void |
public PreprocessLayer ( ILayer layer, INeuralData input, ISynapse source ) : void | ||
layer | ILayer | The layer to process. |
input | INeuralData | The input to this layer. |
source | ISynapse | The source from this layer. |
return | void |