|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectorg.joone.engine.Layer
org.joone.engine.SimpleLayer
org.joone.engine.BiasedLinearLayer
public class BiasedLinearLayer
This layer consists of linear neurons, i.e. neurons that sum up their inputs (actually this is done by the (full) synapse in Joone) along with their biases. In the learning process the biases are adjusted in an attempt to output a value closer to the desired output. This layer differs from LinearLayer in two ways: - This layer uses biases. These biases can/will also be adjusted in the learning process. - It has no scalar beta parameter.
Field Summary |
---|
Fields inherited from class org.joone.engine.Layer |
---|
bias, gradientInps, gradientOuts, inps, inputPatternListeners, learnable, learning, m_batch, monitor, myLearner, outputPatternListeners, outs, running, step, STOP_FLAG |
Constructor Summary | |
---|---|
BiasedLinearLayer()
Creates a new instance of BiasedLinearLayer |
|
BiasedLinearLayer(java.lang.String anElemName)
Creates a new instance of BiasedLinearLayer. |
Method Summary | |
---|---|
void |
backward(double[] pattern)
Reverse transfer function of the component. |
void |
forward(double[] pattern)
Transfer function to recall a result on a trained net |
Learner |
getLearner()
Deprecated. - Used only for backward compatibility |
Methods inherited from class org.joone.engine.SimpleLayer |
---|
getLearningRate, getLrate, getMomentum, setDimensions, setLrate, setMomentum, setMonitor |
Methods inherited from class java.lang.Object |
---|
clone, equals, getClass, hashCode, notify, notifyAll, wait, wait, wait |
Methods inherited from interface org.joone.engine.Learnable |
---|
getMonitor, initLearner |
Methods inherited from interface org.joone.engine.NeuralLayer |
---|
addInputSynapse, addNoise, addOutputSynapse, check, copyInto, getAllInputs, getAllOutputs, getBias, getLayerName, getMonitor, getRows, isRunning, removeAllInputs, removeAllOutputs, removeInputSynapse, removeOutputSynapse, setAllInputs, setAllOutputs, setBias, setLayerName, setMonitor, setRows, start |
Constructor Detail |
---|
public BiasedLinearLayer()
public BiasedLinearLayer(java.lang.String anElemName)
The
- name of the layer.Method Detail |
---|
public void backward(double[] pattern)
Layer
backward
in class SimpleLayer
pattern
- input pattern on which to apply the transfer functionpublic void forward(double[] pattern)
Layer
forward
in class Layer
pattern
- input pattern to which to apply the rtransfer functionpublic Learner getLearner()
Layer
getLearner
in interface Learnable
getLearner
in class Layer
Learnable.getLearner()
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |