Softmin< InputDataType, OutputDataType > Class Template Reference

Implementation of the Softmin layer. More...

Public Member Functions
	Softmin ()
	Create the Softmin object. More...
template < typename eT >
void	Backward (const arma::Mat< eT > &input, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More...
InputDataType &	Delta () const
	Get the delta. More...
InputDataType &	Delta ()
	Modify the delta. 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...
OutputDataType &	OutputParameter () const
	Get the output parameter. More...
OutputDataType &	OutputParameter ()
	Modify the output parameter. More...
template < typename Archive >
void	serialize (Archive &, const uint32_t)
	Serialize the layer. More...

Detailed Description

template

<

typename

InputDataType

=

arma::mat

,

typename

OutputDataType

=

arma::mat

>

class mlpack::ann::Softmin< InputDataType, OutputDataType >

Implementation of the Softmin layer.

The Softmin function takes as a input a vector of K real numbers, rescaling them so that the elements of the K-dimensional output vector lie in the range [0, 1] and sum to 1.

Template Parameters

InputDataType	Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataType	Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Definition at line 35 of file softmin.hpp.

Constructor & Destructor Documentation

Softmin()

Softmin

(

)

Create the Softmin object.

Member Function Documentation

Backward()

void Backward	(	const arma::Mat< eT > &	input,
		const arma::Mat< eT > &	gy,
		arma::Mat< eT > &	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.
gy	The backpropagated error.
g	The calculated gradient.

Delta() [1/2]

InputDataType& Delta ( ) const

inline

Get the delta.

Definition at line 73 of file softmin.hpp.

Delta() [2/2]

InputDataType& Delta ( )

inline

Modify the delta.

Definition at line 75 of file softmin.hpp.

References Softmin< InputDataType, OutputDataType >::serialize().

Forward()

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.

Parameters

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

OutputParameter() [1/2]

OutputDataType& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 68 of file softmin.hpp.

OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 70 of file softmin.hpp.

serialize()

void serialize	(	Archive &	,
		const uint32_t
	)

Serialize the layer.

Referenced by Softmin< InputDataType, OutputDataType >::Delta().

---

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

• /home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/softmin.hpp