类 LinearUnit
java.lang.Object
weka.classifiers.functions.neural.LinearUnit
- 所有已实现的接口:
Serializable
,NeuralMethod
,RevisionHandler
This can be used by the
neuralnode to perform all it's computations (as a Linear unit).
- 版本:
- $Revision: 1.7 $
- 作者:
- Malcolm Ware (mfw4@cs.waikato.ac.nz)
- 另请参阅:
-
构造器概要
构造器 -
方法概要
修饰符和类型方法说明double
errorValue
(NeuralNode node) This function calculates what the error value should be.Returns the revision string.double
outputValue
(NeuralNode node) This function calculates what the output value should be.void
updateWeights
(NeuralNode node, double learn, double momentum) This function will calculate what the change in weights should be and also update them.
-
构造器详细资料
-
LinearUnit
public LinearUnit()
-
-
方法详细资料
-
outputValue
This function calculates what the output value should be.- 指定者:
outputValue
在接口中NeuralMethod
- 参数:
node
- The node to calculate the value for.- 返回:
- The value.
-
errorValue
This function calculates what the error value should be.- 指定者:
errorValue
在接口中NeuralMethod
- 参数:
node
- The node to calculate the error for.- 返回:
- The error.
-
updateWeights
This function will calculate what the change in weights should be and also update them.- 指定者:
updateWeights
在接口中NeuralMethod
- 参数:
node
- The node to update the weights for.learn
- The learning rate to use.momentum
- The momentum to use.
-
getRevision
Returns the revision string.- 指定者:
getRevision
在接口中RevisionHandler
- 返回:
- the revision
-