| EpochTrainer Class |
Inheritance HierarchyNamespace: Imsl.DataMining.Neural
Assembly: ImslCS (in ImslCS.dll) Version: 6.5.2.0
SyntaxThe EpochTrainer type exposes the following members.
Constructors| Name | Description | |
|---|---|---|
 | EpochTrainer(ITrainer) |
Creates a single stage EpochTrainer. Stage II training is
bypassed.
|
| EpochTrainer(ITrainer, ITrainer) |
Creates a two-stage EpochTrainer.
|
Methods| Name | Description | |
|---|---|---|
| Equals | Determines whether the specified object is equal to the current object. (Inherited from Object.) |
 | Finalize | Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection. (Inherited from Object.) |
| GetHashCode | Serves as a hash function for a particular type. (Inherited from Object.) |
| GetType | Gets the Type of the current instance. (Inherited from Object.) |
| MemberwiseClone | Creates a shallow copy of the current Object. (Inherited from Object.) |
| SetRandomSamples |
Sets the random number generators used to select random training
patterns in stage I.
|
| ToString | Returns a string that represents the current object. (Inherited from Object.) |
| Train |
Trains the neural network using supplied training patterns.
|
Properties| Name | Description | |
|---|---|---|
 | EpochSize |
The number of randomly selected training patterns in each stage I
epoch.
|
| ErrorGradient |
The value of the gradient of the error function with respect
to the Weights.
|
| ErrorStatus |
The training error status.
|
| ErrorValue |
The value of the error function.
|
| NumberOfEpochs |
The number of epochs used during stage I training.
|
| Random |
The random number generator used to perturb the stage I guesses.
|
 | Stage1Trainer |
The stage 1 trainer.
|
| Stage2Trainer |
The stage 1 trainer.
|
RemarksThe EpochTrainer, is a meta-trainer that combines two trainers. The first trainer is used on a series of randomly selected subsets of the training patterns. For each subset, the Weights are initialized to their initial values plus a random offset.
Stage II then refines the result found in stage I. The best result from the stage I trainings is used as the initial guess with the second trainer operating on the full set of training patterns. Stage II is optional, if the second trainer is null then the best stage I result is returned as the EpochTrainer's result.
See Also