Holds a level worth of information used by each of the propagation methods. A level is defined as all of the layers that feed a single next layer. In a pure feedforward neural network there will be only one layer per level. However, recurrent neural networks will contain multiple layers per level.

For a list of all members of this type, see PropagationLevel Members .

System.Object
   PropagationLevel

Thread Safety

Public static (Shared in Visual Basic) members of this type are safe for multithreaded operations. Instance members are not guaranteed to be thread-safe.

Requirements

Namespace: Encog.Neural.Networks.Training.Propagation

Assembly: encog-core-cs (in encog-core-cs.dll)

See Also

PropagationLevel Members | Encog.Neural.Networks.Training.Propagation Namespace