MiniDNN::RMSProp Class Reference

#include <RMSProp.h>

Inheritance diagram for MiniDNN::RMSProp:

Public Member Functions
void	reset ()
void	update (ConstAlignedMapVec &dvec, AlignedMapVec &vec)

Public Attributes
Scalar	m_lrate
Scalar	m_eps
Scalar	m_decay

Detailed Description

The RMSProp algorithm

Definition at line 17 of file RMSProp.h.

Member Function Documentation

reset()

void MiniDNN::RMSProp::reset ( )

inlinevirtual

Reset the optimizer to clear all historical information

Reimplemented from MiniDNN::Optimizer.

Definition at line 36 of file RMSProp.h.

update()

void MiniDNN::RMSProp::update ( ConstAlignedMapVec &  dvec, AlignedMapVec &  vec  )

inlinevirtual

Update the parameter vector using its gradient

It is assumed that the memory addresses of dvec and vec do not change during the training process. This is used to implement optimization algorithms that have "memories". See the AdaGrad algorithm for an example.

Parameters

dvec	The gradient of the parameter. Read-only
vec	On entering, the current parameter vector. On exit, the updated parameters.

Implements MiniDNN::Optimizer.

Definition at line 38 of file RMSProp.h.

---

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

• Optimizer/RMSProp.h