mlpack::ann::HardShrink< InputDataType, OutputDataType > Class Template Reference

Hard Shrink operator is defined as,. More...

#include <hardshrink.hpp>

Public Member Functions
	HardShrink (const double lambda=0.5)
	Create HardShrink object using specified hyperparameter lambda. More...
template<typename InputType , typename OutputType >
void	Forward (const InputType &input, OutputType &output)
	Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...
template<typename DataType >
void	Backward (const DataType &input, DataType &gy, DataType &g)
	Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More...
OutputDataType const &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
OutputDataType const &	Delta () const
	Get the delta.
OutputDataType &	Delta ()
	Modify the delta.
double const &	Lambda () const
	Get the hyperparameter lambda.
double &	Lambda ()
	Modify the hyperparameter lambda.
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::HardShrink< InputDataType, OutputDataType >

Hard Shrink operator is defined as,.

\begin{eqnarray*} f(x) &=& \begin{cases} x & : x > lambda \\ x & : x < -lambda \\ 0 & : otherwise. \end{cases} \\ f'(x) &=& \begin{cases} 1 & : x > lambda \\ 1 & : x < -lambda \\ 0 & : otherwise. \end{cases} \end{eqnarray*}

\(\lambda\) is set to 0.5 by default.

Constructor & Destructor Documentation

HardShrink()

template<typename InputDataType , typename OutputDataType >

mlpack::ann::HardShrink< InputDataType, OutputDataType >::HardShrink

(

const double

lambda = 0.5

)

Create HardShrink object using specified hyperparameter lambda.

Parameters

lambda

Is calculated by multiplying the noise level sigma of the input(noisy image) and a coefficient 'a' which is one of the training parameters. Default value of lambda is 0.5.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename DataType >

void mlpack::ann::HardShrink< InputDataType, OutputDataType >::Backward	(	const DataType &	input,
		DataType &	gy,
		DataType &	g
	)

Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f.

Using the results from the feed forward pass.

Parameters

input	The propagated input activation f(x).
gy	The backpropagated error.
g	The calculated gradient.

Forward()

template<typename InputDataType , typename OutputDataType >

template<typename InputType , typename OutputType >

void mlpack::ann::HardShrink< InputDataType, OutputDataType >::Forward	(	const InputType &	input,
		OutputType &	output
	)

Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f.

Parameters

input	Input data used for evaluating the Hard Shrink function.
output	Resulting output activation.

---

The documentation for this class was generated from the following files:

• src/mlpack/methods/ann/layer/hardshrink.hpp
• src/mlpack/methods/ann/layer/hardshrink_impl.hpp