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

Updates according to a modified Hebbian rule (wij += ni * f(x, y)) with additional normalization and zero summing for optimal edge detection. More...

#include <NormalizedZerosumHebbianRule.hpp>

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

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

Public Member Functions
	NormalizedZerosumHebbianRule (size_t rows_, size_t cols_)
virtual	~NormalizedZerosumHebbianRule ()
virtual void	update (mic::types::MatrixPtr< eT > p_, mic::types::MatrixPtr< eT > x_, mic::types::MatrixPtr< eT > y_, eT learning_rate_=0.001)
virtual mic::types::MatrixPtr< eT >	calculateUpdate (mic::types::MatrixPtr< eT > x_, mic::types::MatrixPtr< eT > y_, eT learning_rate_)
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)

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

Detailed Description

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

Updates according to a modified Hebbian rule (wij += ni * f(x, y)) with additional normalization and zero summing for optimal edge detection.

Author

tkornuta/Alexis-Asseman

Definition at line 41 of file NormalizedZerosumHebbianRule.hpp.

Constructor & Destructor Documentation

template<typename eT = float>

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

inline

Constructor. Sets dimensions.

Parameters

rows_	Number of rows of the update matrix.
cols_	Number of columns of the update matrix.

Definition at line 48 of file NormalizedZerosumHebbianRule.hpp.

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

template<typename eT = float>

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

inlinevirtual

Definition at line 54 of file NormalizedZerosumHebbianRule.hpp.

Member Function Documentation

template<typename eT = float>

virtual mic::types::MatrixPtr<eT> mic::neural_nets::learning::NormalizedZerosumHebbianRule< eT >::calculateUpdate ( mic::types::MatrixPtr< eT >  x_, mic::types::MatrixPtr< eT >  y_, eT  learning_rate_  )

inlinevirtual

Calculates the update according to the hebbian rule.

Parameters

x_	Pointer to the input data matrix.
y_	Pointer to the output data matrix.
learning_rate_	Learning rate (default=0.001).

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

Definition at line 88 of file NormalizedZerosumHebbianRule.hpp.

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

Referenced by mic::neural_nets::learning::NormalizedZerosumHebbianRule< eT >::update().

template<typename eT = float>

virtual void mic::neural_nets::learning::NormalizedZerosumHebbianRule< eT >::update ( mic::types::MatrixPtr< eT >  p_, mic::types::MatrixPtr< eT >  x_, mic::types::MatrixPtr< eT >  y_, eT  learning_rate_ = 0.001  )

inlinevirtual

Updates the weight matrix according to the hebbian rule with normalization (l2 norm).

Parameters

p_	Pointer to the parameter (weight) matrix.
x_	Pointer to the input data matrix.
y_	Pointer to the output data matrix.
learning_rate_	Learning rate (default=0.001).

Reimplemented from mic::neural_nets::optimization::OptimizationFunction< eT >.

Definition at line 64 of file NormalizedZerosumHebbianRule.hpp.

References mic::neural_nets::learning::NormalizedZerosumHebbianRule< eT >::calculateUpdate(), and mic::neural_nets::learning::NormalizedZerosumHebbianRule< eT >::delta.

Here is the call graph for this function:

Member Data Documentation

template<typename eT = float>

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

protected

Calculated update.

Definition at line 124 of file NormalizedZerosumHebbianRule.hpp.

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

---

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

• src/optimization/NormalizedZerosumHebbianRule.hpp