Documentation For Encog 2.x

ResilientPropagation Constructor

Construct a resilient training object, allow the training parameters to be specified. Usually the default parameters are acceptable for the resilient training algorithm. Therefore you should usually use the other constructor, that makes use of the default values.

ResilientPropagation(
   BasicNetwork network,
   INeuralDataSet training,
   double zeroTolerance,
   double initialUpdate,
   double maxStep
);

Parameters

network: The network to train.
training: The training set to use.
zeroTolerance: The zero tolerance.
initialUpdate: The initial update values, this is the amount that the deltas are all initially set to.
maxStep: The maximum that a delta can reach.

See Also

ResilientPropagation Class | Encog.Neural.Networks.Training.Propagation.Resilient Namespace | ResilientPropagation Constructor Overload List