Imsl.Datamining.Neural namespace contains feed forward multilayer neural network training and forecasting engines plus algorithms to facilitate data pre- and post-processing.
Classes
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. This is created by a factory method in
Network.
| |
InputLayer |
Input layer in a neural network.
| |
InputNode |
A Node in the InputLayer.
| |
Layer |
The base class for Layers 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. Lagging is done within
the nominal categories associated with the time series.
| |
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. It also reverses the aforementioned encoding,
accepting binary encoded data and returns an array of integers
representing the classes for a nominal variable.
| |
UnsupervisedOrdinalFilter |
Encodes ordinal data into percentages for input to a neural network. It
also allows decoding, accepting a percentage and converting it into an
ordinal value.
|
Structures
Structure | Description | |
---|---|---|
Activation |
Interfaces
Interface | Description | |
---|---|---|
IActivation |
Interface implemented by perceptron activation functions.
| |
ITrainer |
Interface implemented by classes used to train an Network.
| |
QuasiNewtonTrainer..::.IError |
Error function to be minimized by trainer.
|
Enumerations
Enumeration | Description | |
---|---|---|
ScaleFilter..::.ScalingMethod |
Scaling Method
| |
UnsupervisedOrdinalFilter..::.TransformMethod |
Transform type
|