Package | Description |
---|---|
org.simbrain.network.gui.dialogs.network |
The network.gui.dialogs.network package contains dialog classes that manage the creation and editing of
network-level dialog boxes.
|
org.simbrain.network.gui.trainer |
The network.gui.trainer package contains components that can be used to display trainer.
|
org.simbrain.network.subnetworks |
The network.subnetworks package contains all bottom-level subclasses of group.
|
org.simbrain.network.trainers |
The network.trainers package contains supervised learning algorithms.
|
Constructor and Description |
---|
SupervisedTrainingDialog(NetworkPanel np,
Trainable trainable)
Default constructor.
|
Modifier and Type | Method and Description |
---|---|
static javax.swing.Action |
TrainerGuiActions.getEditCombinedDataAction(NetworkPanel networkPanel,
Trainable trainable)
Action for viewing two datatables, one for input data; the other for
training data.
|
Constructor and Description |
---|
TrainingSetPanel(Trainable trainable,
int numVisibleColumnsPerTable)
Construct a new pane for displaying training sets.
|
Modifier and Type | Class and Description |
---|---|
class |
BackpropNetwork
Backprop network.
|
class |
BPTTNetwork
Implements a network to be trained using backprop through time.
|
class |
CompetitiveNetwork
CompetitiveNetwork is a small network encompassing a Competitive
group.
|
class |
Hopfield
Hopfield is a basic implementation of a discrete Hopfield network.
|
class |
LMSNetwork
A Least Mean Squares network.
|
class |
SimpleRecurrentNetwork
Implements a simple recurrent network (See, e.g, Elman 1991).
|
class |
SOMNetwork
SOMNetwork is a small network encompassing an SOM group.
|
Modifier and Type | Field and Description |
---|---|
protected Trainable |
Trainer.network
The trainable object to be trained.
|
Modifier and Type | Method and Description |
---|---|
static Trainable |
Trainer.getTrainable(Group trainedGroup,
java.util.List<Neuron> inputNeurons,
java.util.List<Neuron> outputNeurons,
double[][] inputData,
double[][] targetData)
Utility method for creating a trainable object.
|
Trainable |
Trainer.getTrainableNetwork() |
Modifier and Type | Method and Description |
---|---|
protected int |
IterableTrainer.getMinimumNumRows(Trainable network)
Returns the number of rows in whichever dataset has fewer rows.
|
void |
LMSOffline.moorePenroseSolution(Trainable network)
Moore penrose.
|
void |
LMSOffline.weinerHopfSolution(Trainable network)
Implements the Wiener-Hopf solution to LMS linear regression.
|
Constructor and Description |
---|
BackpropTrainer(Trainable network,
java.util.List<java.util.List<Neuron>> layers)
Construct the backprop trainer.
|
IterableTrainer(Trainable network)
Construct the iterable trainer.
|
LMSIterative(Trainable network)
Construct a least mean squares iterative panel.
|
LMSOffline(Trainable network)
Construct the LMSOOffline object, with a trainable network the Synapse
group where the new synapses will be placed.
|
Trainer(Trainable network)
Construct the trainer and pass in a reference to the trainable element.
|