ROOT   Reference Guide
TMVA::DNN::Steepest Class Reference

Steepest Gradient Descent algorithm (SGD)

Implements a steepest gradient descent minimization algorithm

Definition at line 332 of file NeuralNet.h.

## Public Member Functions

Steepest (double learningRate=1e-4, double momentum=0.5, size_t repetitions=10)
c'tor More...

template<typename Function , typename Weights , typename PassThrough >
double operator() (Function &fitnessFunction, Weights &weights, PassThrough &passThrough)
operator to call the steepest gradient descent algorithm More...

## Public Attributes

double m_alpha
internal parameter (learningRate) More...

double m_beta
internal parameter (momentum) More...

local gradients for reuse in thread. More...

std::vector< doublem_localWeights
local weights for reuse in thread. More...

vector remembers the gradients of the previous step More...

size_t m_repetitions

#include <TMVA/NeuralNet.h>

## ◆ Steepest()

 TMVA::DNN::Steepest::Steepest ( double learningRate = 1e-4, double momentum = 0.5, size_t repetitions = 10 )
inline

c'tor

C'tor

Parameters
 learningRate denotes the learning rate for the SGD algorithm momentum fraction of the velocity which is taken over from the last step repetitions re-compute the gradients each "repetitions" steps

Definition at line 347 of file NeuralNet.h.

## ◆ operator()()

template<typename Function , typename Weights , typename PassThrough >
 double TMVA::DNN::Steepest::operator() ( Function & fitnessFunction, Weights & weights, PassThrough & passThrough )

operator to call the steepest gradient descent algorithm

implementation of the steepest gradient descent algorithm

entry point to start the minimization procedure

Parameters
 fitnessFunction (templated) function which has to be provided. This function is minimized weights (templated) a reference to a container of weights. The result of the minimization procedure is returned via this reference (needs to support std::begin and std::end passThrough (templated) object which can hold any data which the fitness function needs. This object is not touched by the minimizer; This object is provided to the fitness function when called

Can be used with multithreading (i.e. "HogWild!" style); see call in trainCycle

Definition at line 271 of file NeuralNet.icc.

## ◆ m_alpha

 double TMVA::DNN::Steepest::m_alpha

internal parameter (learningRate)

Definition at line 370 of file NeuralNet.h.

## ◆ m_beta

 double TMVA::DNN::Steepest::m_beta

internal parameter (momentum)

Definition at line 371 of file NeuralNet.h.

Definition at line 375 of file NeuralNet.h.

## ◆ m_localWeights

 std::vector TMVA::DNN::Steepest::m_localWeights

local weights for reuse in thread.

Definition at line 374 of file NeuralNet.h.

vector remembers the gradients of the previous step

Definition at line 372 of file NeuralNet.h.

## ◆ m_repetitions

 size_t TMVA::DNN::Steepest::m_repetitions

Definition at line 336 of file NeuralNet.h.

Libraries for TMVA::DNN::Steepest:
[legend]

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