mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT > Class Template Reference

Updates according to classical Hebbian rule (wij += ni * x * y). More...

#include <BinaryCorrelatorLearningRule.hpp>

Inheritance diagram for mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >:

Collaboration diagram for mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >:

Public Member Functions
	BinaryCorrelatorLearningRule (size_t rows_, size_t cols_)
virtual	~BinaryCorrelatorLearningRule ()
virtual mic::types::MatrixPtr< eT >	calculateUpdate (mic::types::MatrixPtr< eT > x_, mic::types::MatrixPtr< eT > y_, eT ni_aa=0.1)
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)

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

Detailed Description

template<typename eT = float>
class mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >

Updates according to classical Hebbian rule (wij += ni * x * y).

Author

tkornuta

tkornuta

Definition at line 43 of file BinaryCorrelatorLearningRule.hpp.

Constructor & Destructor Documentation

template<typename eT = float>

mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >::BinaryCorrelatorLearningRule ( size_t  rows_, size_t  cols_  )

inline

Constructor. Sets dimensions, momentum rates (beta1=0.9 and beta2=0.999) and eps(default=1e-8).

Parameters

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

Definition at line 50 of file BinaryCorrelatorLearningRule.hpp.

References mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >::delta.

template<typename eT = float>

virtual mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >::~BinaryCorrelatorLearningRule ( )

inlinevirtual

Definition at line 56 of file BinaryCorrelatorLearningRule.hpp.

Member Function Documentation

template<typename eT = float>

virtual mic::types::MatrixPtr<eT> mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >::calculateUpdate ( mic::types::MatrixPtr< eT >  x_, mic::types::MatrixPtr< eT >  y_, eT  ni_aa = 0.1  )

inlinevirtual

Calculates the update according to the hebbian rule.

Parameters

x_	Pointer to the input data matrix.
y_	Pointer to the output data matrix.
ni_aa	Learning rate for P({AA}) (default=0.1).

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

Definition at line 65 of file BinaryCorrelatorLearningRule.hpp.

References mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >::delta.

Member Data Documentation

template<typename eT = float>

mic::types::MatrixPtr<eT> mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >::delta

protected

Calculated update.

Definition at line 91 of file BinaryCorrelatorLearningRule.hpp.

Referenced by mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >::BinaryCorrelatorLearningRule(), and mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >::calculateUpdate().

---

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

• src/optimization/BinaryCorrelatorLearningRule.hpp