Defines the specifics to one of the propagation methods. The individual ways that each of the propagation methods uses to modify the weight and] threshold matrix are defined here.
For a list of all members of this type, see IPropagationMethod Members .
| Type | Description |
|---|---|
| BackpropagationMethod | This class implements the specifics of how the backpropagation algorithm is used. Specifically, the partial derivatives are simply applied to the weight matrix. |
| ManhattanPropagationMethod | Implements the specifics of the Manhattan propagation algorithm. This class actually handles the updates to the weight matrix. |
| ResilientPropagationMethod | Implements the specifics of the resilient propagation training algorithm. |
Namespace: Encog.Neural.Networks.Training.Propagation
Assembly: encog-core-cs (in encog-core-cs.dll)
IPropagationMethod Members | Encog.Neural.Networks.Training.Propagation Namespace