SHOGUN  4.1.0
 全部  命名空间 文件 函数 变量 类型定义 枚举 枚举值 友元 宏定义  
所有成员列表 | Public 成员函数
DescendUpdater类 参考abstract

详细描述

This is a base class for descend update.

The class give the interface used in descend-based minimizer.

Given a target variable, \(w\), and its negative descend direction \(g\), the class will update \(w\) based on \(g\) (eg, subtracting \(g\))

Note that an example of \(g\) is to simply use the gradient wrt \(w\).

在文件 DescendUpdater.h49 行定义.

类 DescendUpdater 继承关系图:
Inheritance graph
[图例]

Public 成员函数

virtual void update_variable (SGVector< float64_t > variable_reference, SGVector< float64_t > negative_descend_direction, float64_t learning_rate)=0
 
virtual void update_context (CMinimizerContext *context)=0
 
virtual void load_from_context (CMinimizerContext *context)=0
 

成员函数说明

virtual void load_from_context ( CMinimizerContext context)
pure virtual

Load the given context object to restore mutable variables

This method will be called by FirstOrderMinimizer::load_from_context(CMinimizerContext* context)

参数
contexta context object

DescendUpdaterWithCorrection, AdaDeltaUpdater, RmsPropUpdater , 以及 AdaGradUpdater 内被实现.

virtual void update_context ( CMinimizerContext context)
pure virtual

Update a context object to store mutable variables used in descend update

This method will be called by FirstOrderMinimizer::save_to_context()

参数
contexta context object

DescendUpdaterWithCorrection, AdaDeltaUpdater, RmsPropUpdater , 以及 AdaGradUpdater 内被实现.

virtual void update_variable ( SGVector< float64_t variable_reference,
SGVector< float64_t negative_descend_direction,
float64_t  learning_rate 
)
pure virtual

Update the target variable based on the given negative descend direction

Note that this method will update the target variable in place. This method will be called by FirstOrderMinimizer::minimize()

参数
variable_referencea reference of the target variable
negative_descend_directionthe negative descend direction given the current value
learning_ratelearning rate

AdaDeltaUpdater, RmsPropUpdater, AdaGradUpdater , 以及 DescendUpdaterWithCorrection 内被实现.


该类的文档由以下文件生成:

SHOGUN 机器学习工具包 - 项目文档