public final class SimpleRecurrentNetwork extends Subnetwork implements Trainable
Constructor and Description |
---|
SimpleRecurrentNetwork(Network network,
int numInputNodes,
int numHiddenNodes,
int numOutputNodes)
Build an SRN with default activation rules and initial position.
|
SimpleRecurrentNetwork(Network network,
int numInputNodes,
int numHiddenNodes,
int numOutputNodes,
NeuronUpdateRule hiddenNeuronType,
NeuronUpdateRule outputNeuronType,
java.awt.geom.Point2D initialPosition)
Constructor specifying root network, and number of nodes in each layer.
|
Modifier and Type | Method and Description |
---|---|
NeuronGroup |
getContextLayer() |
NeuronGroup |
getHiddenLayer() |
NeuronGroup |
getInputLayer() |
java.util.List<Neuron> |
getInputNeurons()
Returns the list of input neurons.
|
Group |
getNetwork()
Returns a reference to the subnetwork or synapse group being trained.
|
java.util.List<java.util.List<Neuron>> |
getNeuronGroupsAsList()
Return neuron groups as a list.
|
NeuronGroup |
getOutputLayer() |
java.util.List<Neuron> |
getOutputNeurons()
Returns the list of output neurons.
|
TrainingSet |
getTrainingSet()
Returns the the training set, which contains input and target data.
|
java.lang.String |
getUpdateMethodDesecription()
Returns a description of this group's update method, which is displayed
in the update manager panel.
|
void |
initNetwork()
Initialize the network.
|
void |
update()
Update this group.
|
addAndLabelSynapseGroup, addNeuronGroup, addRowToTrainingSet, addSynapseGroup, clearActivations, connectNeuronGroups, connectNeuronGroups, connectNeuronGroups, delete, displayNeuronGroups, getEnabled, getFlatNeuronList, getFlatSynapseList, getIndexOfNeuronGroup, getLongDescription, getModifiableNeuronList, getNeuronGroup, getNeuronGroup, getNeuronGroupByLabel, getNeuronGroupCount, getNeuronGroupList, getSynapseGroup, getSynapseGroup, getSynapseGroupByLabel, getSynapseGroupCount, getSynapseGroupList, isEmpty, recursivelySetIds, removeNeuronGroup, removeSynapseGroup, setDisplayNeuronGroups, setEnabled, size, toString
getId, getLabel, getParentGroup, getParentNetwork, getStateInfo, hasParentGroup, isMarkedForDeletion, isTopLevelGroup, setId, setLabel, setMarkedForDeletion, setParentGroup, setStateInfo
public SimpleRecurrentNetwork(Network network, int numInputNodes, int numHiddenNodes, int numOutputNodes)
network
- underlying networknumInputNodes
- number of nodes in the input layernumHiddenNodes
- number of nodes in the hidden and context layersnumOutputNodes
- number of output nodespublic SimpleRecurrentNetwork(Network network, int numInputNodes, int numHiddenNodes, int numOutputNodes, NeuronUpdateRule hiddenNeuronType, NeuronUpdateRule outputNeuronType, java.awt.geom.Point2D initialPosition)
network
- underlying networknumInputNodes
- number of nodes in the input layernumHiddenNodes
- number of nodes in the hidden and context layersnumOutputNodes
- number of output nodeshiddenNeuronType
- update rule for hidden nodesoutputNeuronType
- update rule for hidden nodesinitialPosition
- where to position the network (upper left)public void initNetwork()
Trainable
initNetwork
in interface Trainable
public void update()
Group
update
in class Subnetwork
public java.util.List<java.util.List<Neuron>> getNeuronGroupsAsList()
getNeuronGroupsAsList
in class Subnetwork
public java.util.List<Neuron> getInputNeurons()
getInputNeurons
in interface Trainable
public java.util.List<Neuron> getOutputNeurons()
getOutputNeurons
in interface Trainable
public TrainingSet getTrainingSet()
getTrainingSet
in interface Trainable
public NeuronGroup getContextLayer()
public NeuronGroup getHiddenLayer()
public NeuronGroup getInputLayer()
public NeuronGroup getOutputLayer()
public java.lang.String getUpdateMethodDesecription()
getUpdateMethodDesecription
in class Subnetwork
public Group getNetwork()
getNetwork
in interface Trainable