|
||||||||||
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.LinearLayer
org.joone.engine.SoftmaxLayer
public class SoftmaxLayer
The outputs of the Softmax layer must be interpreted as probabilities. The output of each node, in fact, ranges from 0 and 1, and the sum of all the nodes is always 1. Useful to implement the 1 of C classification network.
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 | |
---|---|
SoftmaxLayer()
Creates a new instance of SoftmaxLayer |
Method Summary | |
---|---|
void |
forward(double[] pattern)
Transfer function to recall a result on a trained net |
Methods inherited from class org.joone.engine.LinearLayer |
---|
backward, getBeta, Inspections, setBeta |
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 |
Constructor Detail |
---|
public SoftmaxLayer()
Method Detail |
---|
public void forward(double[] pattern)
Layer
forward
in class LinearLayer
pattern
- input pattern to which to apply the rtransfer function
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |