This interface defines all necessary methods for a neural network layer.
For a list of all members of this type, see ILayer Members .
| Type | Description |
|---|---|
| BasicLayer | Basic functionality that most of the neural layers require. The basic layer is often used by itself to implement forward or recurrent layers. Other layer types are based on the basic layer as well. The layer will either have thresholds are not. Thresholds are values that correspond to each of the neurons. The threshold values will be added to the output calculated for each neuron. Together with the weight matrix the threshold values make up the memory of the neural network. When the neural network is trained, these threshold values (along with the weight matrix values) will be modified. |
| ContextLayer | Implements a context layer. A context layer is used to implement a simple recurrent neural network, such as an Elman or Jordan neural network. The context layer has a short-term memory. The context layer accept input, and provide the same data as output on the next cycle. This continues, and the context layer's output "one step" out of sync with the input. |
| RadialBasisFunctionLayer | This layer type makes use of several radial basis function to scale the output from this layer. Each RBF can have a different center, peak, and width. Proper selection of these values will greatly impact the success of the layer. Currently, Encog provides no automated way of determining these values. There is one RBF per neuron. Radial basis function layers have neither thresholds nor a regular activation function. Calling any methods that deal with the activation function or thresholds will result in an error. |
Namespace: Encog.Neural.Networks.Layers
Assembly: encog-core-cs (in encog-core-cs.dll)