mic::neural_nets::loss::SquaredErrorLoss< dtype > Class Template Reference

Class representing a squared error loss function (regression). L = 1/2 sum (t - p)^2. More...

#include <SquaredErrorLoss.hpp>

Inheritance diagram for mic::neural_nets::loss::SquaredErrorLoss< dtype >:

Collaboration diagram for mic::neural_nets::loss::SquaredErrorLoss< dtype >:

Public Member Functions
dtype	calculateLoss (mic::types::MatrixPtr< dtype > target_y_, mic::types::MatrixPtr< dtype > predicted_y_)
	Function calculates squared difference loss (regression) and returns squared error (SE). More...
mic::types::MatrixPtr< dtype >	calculateGradient (mic::types::MatrixPtr< dtype > target_y_, mic::types::MatrixPtr< dtype > predicted_y_)
	Function calculating gradient - for squared difference (regression). More...
Public Member Functions inherited from mic::neural_nets::loss::Loss< dtype >
virtual dtype	calculateMeanLoss (mic::types::MatrixPtr< dtype > target_y_, mic::types::MatrixPtr< dtype > predicted_y_)
	Calculates mean loss (i.e. divides the loss by the size of batch) - ACE for cross-entropy or MSE for regression. More...

Detailed Description

template<typename dtype = float>
class mic::neural_nets::loss::SquaredErrorLoss< dtype >

Class representing a squared error loss function (regression). L = 1/2 sum (t - p)^2.

Author

tkornuta

Template Parameters

dtype

Template parameter denoting precision of variables.

Definition at line 41 of file SquaredErrorLoss.hpp.

Member Function Documentation

template<typename dtype = float>

mic::types::MatrixPtr<dtype> mic::neural_nets::loss::SquaredErrorLoss< dtype >::calculateGradient ( mic::types::MatrixPtr< dtype >  target_y_, mic::types::MatrixPtr< dtype >  predicted_y_  )

inlinevirtual

Function calculating gradient - for squared difference (regression).

Implements mic::neural_nets::loss::Loss< dtype >.

Definition at line 63 of file SquaredErrorLoss.hpp.

Referenced by TEST_F().

template<typename dtype = float>

dtype mic::neural_nets::loss::SquaredErrorLoss< dtype >::calculateLoss ( mic::types::MatrixPtr< dtype >  target_y_, mic::types::MatrixPtr< dtype >  predicted_y_  )

inlinevirtual

Function calculates squared difference loss (regression) and returns squared error (SE).

Implements mic::neural_nets::loss::Loss< dtype >.

Definition at line 46 of file SquaredErrorLoss.hpp.

Referenced by TEST_F().

---

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

• src/loss/SquaredErrorLoss.hpp