mic::neural_nets::optimization::GradientDescent< eT > Class Template Reference

Update in the direction of gradient descent. More...

#include <GradientDescent.hpp>

Inheritance diagram for mic::neural_nets::optimization::GradientDescent< eT >:

Collaboration diagram for mic::neural_nets::optimization::GradientDescent< eT >:

Public Member Functions
	GradientDescent (size_t rows_, size_t cols_)
mic::types::MatrixPtr< eT >	calculateUpdate (mic::types::MatrixPtr< eT > x_, mic::types::MatrixPtr< eT > dx_, eT learning_rate_=0.001)
Public Member Functions inherited from mic::neural_nets::optimization::OptimizationFunction< eT >
	OptimizationFunction ()
virtual	~OptimizationFunction ()
	Virtual destructor - empty. More...
virtual void	update (mic::types::MatrixPtr< eT > p_, mic::types::MatrixPtr< eT > dp_, eT learning_rate_, eT decay_=0.0)
virtual void	update (mic::types::MatrixPtr< eT > p_, mic::types::MatrixPtr< eT > x_, mic::types::MatrixPtr< eT > y_, eT learning_rate_=0.001)

Private Attributes
mic::types::MatrixPtr< eT >	delta
	Calculated update. More...

Detailed Description

template<typename eT = float>
class mic::neural_nets::optimization::GradientDescent< eT >

Update in the direction of gradient descent.

Author

tkornuta

Definition at line 39 of file GradientDescent.hpp.

Constructor & Destructor Documentation

template<typename eT = float>

mic::neural_nets::optimization::GradientDescent< eT >::GradientDescent ( size_t  rows_, size_t  cols_  )

inline

Constructor. Sets dimensions.

Parameters

rows_	Number of rows of the updated matrix/its gradient.
cols_	Number of columns of the updated matrix/its gradient.

Definition at line 47 of file GradientDescent.hpp.

References mic::neural_nets::optimization::GradientDescent< eT >::delta.

Member Function Documentation

template<typename eT = float>

mic::types::MatrixPtr<eT> mic::neural_nets::optimization::GradientDescent< eT >::calculateUpdate ( mic::types::MatrixPtr< eT >  x_, mic::types::MatrixPtr< eT >  dx_, eT  learning_rate_ = 0.001  )

inlinevirtual

Calculates the update in the direction of gradient descent.

Parameters

x_	Pointer to the current matrix.
dx_	Pointer to current gradient of that matrix.
learning_rate_	Learning rate (default=0.001).

Implements mic::neural_nets::optimization::OptimizationFunction< eT >.

Definition at line 59 of file GradientDescent.hpp.

References mic::neural_nets::optimization::GradientDescent< eT >::delta.

Member Data Documentation

template<typename eT = float>

mic::types::MatrixPtr<eT> mic::neural_nets::optimization::GradientDescent< eT >::delta

private

Calculated update.

Definition at line 71 of file GradientDescent.hpp.

Referenced by mic::neural_nets::optimization::GradientDescent< eT >::calculateUpdate(), and mic::neural_nets::optimization::GradientDescent< eT >::GradientDescent().

---

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

• src/optimization/GradientDescent.hpp