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

Class representing a log-likelihood cost (to be used with softmax logistic regression). More...

#include <LogLikelihoodLoss.hpp>

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

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

Public Member Functions
dtype	calculateLoss (mic::types::MatrixPtr< dtype > target_y_, mic::types::MatrixPtr< dtype > predicted_y_)
	Calculates log-likelihood cost. More...
mic::types::MatrixPtr< dtype >	calculateGradient (mic::types::MatrixPtr< dtype > target_y_, mic::types::MatrixPtr< dtype > predicted_y_)
	Gradient calculation for log-likelihood cost. NOT FINISHED!! 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::LogLikelihoodLoss< dtype >

Class representing a log-likelihood cost (to be used with softmax logistic regression).

Author

tkornuta

Template Parameters

dtype

Template parameter denoting precision of variables.

Definition at line 46 of file LogLikelihoodLoss.hpp.

Member Function Documentation

template<typename dtype = float>

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

inlinevirtual

Gradient calculation for log-likelihood cost. NOT FINISHED!!

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

Definition at line 74 of file LogLikelihoodLoss.hpp.

template<typename dtype = float>

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

inlinevirtual

Calculates log-likelihood cost.

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

Definition at line 51 of file LogLikelihoodLoss.hpp.

---

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

• src/loss/LogLikelihoodLoss.hpp