dnn::opt_SGD_nesterov Class Reference

Stochastic Gradient Descent with Nesterov momentum optimizer class. More...

#include <dnn_opt.h>

Inheritance diagram for dnn::opt_SGD_nesterov:

Public Member Functions
	opt_SGD_nesterov (DNN_Dtype s, DNN_Dtype m, DNN_Dtype l=0.0, DNN_Dtype a=0.0)
	SGD with Nesterov momentum constructor. More...
	~opt_SGD_nesterov ()
void	apply (arma::Cube< DNN_Dtype > &W, arma::Mat< DNN_Dtype > &B, const arma::Cube< DNN_Dtype > &Wgrad, const arma::Mat< DNN_Dtype > &Bgrad)
	Apply the optimizer to the layer parameters. More...
std::string	get_algorithm (void)
	Get the optimizer algorithm information. More...
Public Member Functions inherited from dnn::opt
	opt ()
	~opt ()
void	set_learn_rate_alg (LR_ALG alg, DNN_Dtype a=0.0, DNN_Dtype b=10.0)
	Set learning rate algorithm. More...
void	update_learn_rate (void)
	Update learning rate. More...
DNN_Dtype	get_learn_rate (void)
	Get the learning rate. More...

Private Attributes
arma::Cube< DNN_Dtype >	v
arma::Cube< DNN_Dtype >	vp
arma::Mat< DNN_Dtype >	vB
arma::Mat< DNN_Dtype >	vBp
DNN_Dtype	mom

Additional Inherited Members
Protected Attributes inherited from dnn::opt
std::string	alg
DNN_Dtype	lr
	Learning rate. More...
DNN_Dtype	reg_lambda
	Regularisation parameter lambda. More...
DNN_Dtype	reg_alpha
	Elastic net mix parameter - 0=ridge (L2) .. 1=LASSO (L1) More...
LR_ALG	lr_alg
	Learning rate schedule algorithm. More...
DNN_Dtype	lr_0
	Init value for lr. More...
DNN_Dtype	lr_a
	Internal parameter a. More...
DNN_Dtype	lr_b
	Internal parameter b. More...
arma::uword	it
	Iteration counter. More...

Detailed Description

Stochastic Gradient Descent with Nesterov momentum optimizer class.

SGD with Nesterov momentum algorithm, see https://arxiv.org/pdf/1609.04747.pdf

Definition at line 271 of file dnn_opt.h.

Constructor & Destructor Documentation

opt_SGD_nesterov()

dnn::opt_SGD_nesterov::opt_SGD_nesterov ( DNN_Dtype  s, DNN_Dtype  m, DNN_Dtype  l = 0.0, DNN_Dtype  a = 0.0  )

inline

SGD with Nesterov momentum constructor.

Parameters

[in]	s	Step size - learning rate
[in]	m	Momentum
[in]	l	Regularisation param lambda
[in]	a	Regularisation param alpha

Definition at line 287 of file dnn_opt.h.

~opt_SGD_nesterov()

dnn::opt_SGD_nesterov::~opt_SGD_nesterov ( )

inline

Definition at line 297 of file dnn_opt.h.

Member Function Documentation

apply()

void dnn::opt_SGD_nesterov::apply ( arma::Cube< DNN_Dtype > &  W, arma::Mat< DNN_Dtype > &  B, const arma::Cube< DNN_Dtype > &  Wgrad, const arma::Mat< DNN_Dtype > &  Bgrad  )

inlinevirtual

Apply the optimizer to the layer parameters.

Parameters

[in,out]	W,B	Learnable parameters
[in]	Wgrad,Bgrad	Gradient of the learnable parameters

Implements dnn::opt.

Definition at line 304 of file dnn_opt.h.

get_algorithm()

std::string dnn::opt_SGD_nesterov::get_algorithm ( void  )

inlinevirtual

Get the optimizer algorithm information.

Returns

Algorithm information string

Reimplemented from dnn::opt.

Definition at line 341 of file dnn_opt.h.

Member Data Documentation

mom

DNN_Dtype dnn::opt_SGD_nesterov::mom

private

Definition at line 278 of file dnn_opt.h.

v

arma::Cube<DNN_Dtype> dnn::opt_SGD_nesterov::v

private

Definition at line 274 of file dnn_opt.h.

vB

arma::Mat<DNN_Dtype> dnn::opt_SGD_nesterov::vB

private

Definition at line 276 of file dnn_opt.h.

vBp

arma::Mat<DNN_Dtype> dnn::opt_SGD_nesterov::vBp

private

Definition at line 277 of file dnn_opt.h.

vp

arma::Cube<DNN_Dtype> dnn::opt_SGD_nesterov::vp

private

Definition at line 275 of file dnn_opt.h.

---

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

• dnn_opt.h