dl::loss::MSELoss< T > Class Template Reference

Mean Squared Error Loss with autograd support. More...

#include <losses.hpp>

Inheritance diagram for dl::loss::MSELoss< T >:

Collaboration diagram for dl::loss::MSELoss< T >:

Public Member Functions
	MSELoss (const std::string &reduction="mean")
	Constructor.
Variable< T >	forward (const Variable< T > &predictions, const Variable< T > &targets) override
	Forward pass: compute MSE loss.
Public Member Functions inherited from dl::loss::AutogradLoss< T >
virtual	~AutogradLoss ()=default
Variable< T >	operator() (const Variable< T > &predictions, const Variable< T > &targets)
	Convenience operator for computing loss.

Detailed Description

template<typename T>
class dl::loss::MSELoss< T >

Mean Squared Error Loss with autograd support.

MSE(y_pred, y_true) = (1/n) * sum((y_pred - y_true)²)

Commonly used for regression tasks.

Definition at line 55 of file losses.hpp.

Constructor & Destructor Documentation

MSELoss()

template<typename T >

dl::loss::MSELoss< T >::MSELoss ( const std::string &  reduction = "mean" )

inlineexplicit

Constructor.

Parameters

reduction

Type of reduction ('mean', 'sum', 'none')

Definition at line 61 of file losses.hpp.

Member Function Documentation

forward()

template<typename T >

Variable< T > dl::loss::MSELoss< T >::forward ( const Variable< T > &  predictions, const Variable< T > &  targets  )

overridevirtual

Forward pass: compute MSE loss.

Parameters

predictions	Predicted values
targets	Target values

Returns

MSE loss

Implements dl::loss::AutogradLoss< T >.

Definition at line 12 of file losses.cpp.

---

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

• include/loss/losses.hpp
• src/loss/losses.cpp