deepboof.impl.backward.standard

Class DActivationTanH_F64

java.lang.Object

deepboof.impl.forward.standard.BaseFunction<T>

deepboof.impl.backward.standard.BaseDFunction<T>

deepboof.impl.backward.standard.ElementWiseDFunction<deepboof.tensors.Tensor_F64>

deepboof.impl.backward.standard.DActivationTanH_F64

All Implemented Interfaces:

DActivationTanH<deepboof.tensors.Tensor_F64>, deepboof.DFunction<deepboof.tensors.Tensor_F64>, deepboof.forward.ActivationTanH<deepboof.tensors.Tensor_F64>, deepboof.Function<deepboof.tensors.Tensor_F64>

public class DActivationTanH_F64
extends ElementWiseDFunction<deepboof.tensors.Tensor_F64>
implements DActivationTanH<deepboof.tensors.Tensor_F64>

Implementation of DActivationTanH for Tensor_F64. Forward pass tanh is cached to reduce computations in backwards pass.

Field Summary

Fields inherited from class deepboof.impl.backward.standard.BaseDFunction

learningMode

Fields inherited from class deepboof.impl.forward.standard.BaseFunction

miniBatchSize, parameters, shapeInput, shapeOutput, shapeParameters

Constructor Summary

Constructors

Constructor and Description
DActivationTanH_F64()

Method Summary

Modifier and Type	Method and Description
protected void	_backwards(deepboof.tensors.Tensor_F64 input, deepboof.tensors.Tensor_F64 dout, deepboof.tensors.Tensor_F64 gradientInput, java.util.List<deepboof.tensors.Tensor_F64> gradientParameters)
void	_forward(deepboof.tensors.Tensor_F64 input, deepboof.tensors.Tensor_F64 output)
java.lang.Class<deepboof.tensors.Tensor_F64>	getTensorType()

Methods inherited from class deepboof.impl.backward.standard.ElementWiseDFunction

_initialize, _setParameters

Methods inherited from class deepboof.impl.backward.standard.BaseDFunction

backwards, evaluating, isLearning, learning

Methods inherited from class deepboof.impl.forward.standard.BaseFunction

forward, getOutputShape, getParameters, getParameterShapes, initialize, setParameters

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface deepboof.DFunction

backwards, evaluating, isLearning, learning

Methods inherited from interface deepboof.Function

forward, getOutputShape, getParameters, getParameterShapes, initialize, setParameters

Constructor Detail

DActivationTanH_F64

public DActivationTanH_F64()

Method Detail

_backwards

protected void _backwards(deepboof.tensors.Tensor_F64 input,
                          deepboof.tensors.Tensor_F64 dout,
                          deepboof.tensors.Tensor_F64 gradientInput,
                          java.util.List<deepboof.tensors.Tensor_F64> gradientParameters)

Specified by:

_backwards in class BaseDFunction<deepboof.tensors.Tensor_F64>

_forward

public void _forward(deepboof.tensors.Tensor_F64 input,
                     deepboof.tensors.Tensor_F64 output)

Specified by:

_forward in class deepboof.impl.forward.standard.BaseFunction<deepboof.tensors.Tensor_F64>

getTensorType

public java.lang.Class<deepboof.tensors.Tensor_F64> getTensorType()

Specified by:

getTensorType in interface deepboof.Function<deepboof.tensors.Tensor_F64>