Interface | Description |
---|---|
Activation |
Interface implemented by perceptron activation functions.
|
QuasiNewtonTrainer.Error |
Error function to be minimized by trainer.
|
Trainer |
Interface implemented by classes used to train a network.
|
Class | Description |
---|---|
BinaryClassification |
Classifies patterns into two classes.
|
EpochTrainer |
Two-stage training using randomly selected training patterns in stage I.
|
FeedForwardNetwork |
A representation of a feed forward neural network.
|
HiddenLayer |
Hidden layer in a neural network.
|
InputLayer |
Input layer in a neural network.
|
InputNode |
A
Node in the InputLayer . |
Layer |
The base class for
Layer s in a neural network. |
LeastSquaresTrainer |
Trains a
FeedForwardNetwork using a Levenberg-Marquardt
algorithm for minimizing a sum of squares error. |
Link |
A link in a neural network.
|
MultiClassification |
Classifies patterns into three or more classes.
|
Network |
Neural network base class.
|
Node |
A
Node in a neural network. |
OutputLayer |
Output layer in a neural network.
|
OutputPerceptron |
A
Perceptron in the OutputLayer . |
Perceptron |
A
Perceptron node in a neural network. |
QuasiNewtonTrainer |
Trains a network using the quasi-Newton method,
MinUnconMultiVar . |
ScaleFilter |
Scales or unscales continuous data prior to its use in neural network
training, testing, or forecasting.
|
TimeSeriesClassFilter |
Converts time series data contained within nominal categories to a lagged
format for processing by a neural network.
|
TimeSeriesFilter |
Converts time series data to a lagged format used as input to a neural network.
|
UnsupervisedNominalFilter |
Converts nominal data into a series of binary encoded
columns for input to a neural network.
|
UnsupervisedOrdinalFilter |
Encodes ordinal data into percentages for input to a neural network.
|
Copyright © 1970-2015 Rogue Wave Software
Built October 13 2015.