nest::WeightOptimizerCommonPropertiesGradientDescent Class Reference

Class implementing common properties of a gradient descent weight optimizer model. More...

#include <weight_optimizer.h>

Inheritance diagram for nest::WeightOptimizerCommonPropertiesGradientDescent:

Collaboration diagram for nest::WeightOptimizerCommonPropertiesGradientDescent:

Public Member Functions
	WeightOptimizerCommonPropertiesGradientDescent ()
	Default constructor.
	WeightOptimizerCommonPropertiesGradientDescent (const WeightOptimizerCommonPropertiesGradientDescent &)=default
	Copy constructor.
WeightOptimizerCommonPropertiesGradientDescent &	operator= (const WeightOptimizerCommonPropertiesGradientDescent &)=delete
	Assignment operator.
WeightOptimizerCommonProperties *	clone () const override
	Clone constructor.
WeightOptimizer *	get_optimizer () const override
	Get optimizer.
std::string	get_name () const override
	Get optimizer name.
Public Member Functions inherited from nest::WeightOptimizerCommonProperties
	WeightOptimizerCommonProperties ()
	Default constructor.
virtual	~WeightOptimizerCommonProperties ()
	Destructor.
	WeightOptimizerCommonProperties (const WeightOptimizerCommonProperties &)
	Copy constructor.
WeightOptimizer &	operator= (const WeightOptimizer &)=delete
	Assignment operator.
virtual void	get_status (Dictionary &d) const
	Get parameter dictionary.
virtual void	set_status (const Dictionary &d)
	Update parameters in parameter dictionary.
double	get_Wmin () const
	Get minimal value for synaptic weight.
double	get_Wmax () const
	Get maximal value for synaptic weight.

Friends
class	WeightOptimizerGradientDescent
	Friend class for gradient descent weight optimizer model.

Additional Inherited Members
Public Attributes inherited from nest::WeightOptimizerCommonProperties
size_t	batch_size_
	Size of an optimization batch.
double	eta_
	Common learning rate for all synapses.
double	eta_first_change_
	First non-default learning rate.
long	eta_change_count_
	Count of learning rate changes so far in the simulation to identify the first change.
double	Wmin_
	Minimal value for synaptic weight.
double	Wmax_
	Maximal value for synaptic weight.
bool	optimize_each_step_
	If true, optimize each step, else once per spike.

Detailed Description

Class implementing common properties of a gradient descent weight optimizer model.

Constructor & Destructor Documentation

WeightOptimizerCommonPropertiesGradientDescent() [1/2]

nest::WeightOptimizerCommonPropertiesGradientDescent::WeightOptimizerCommonPropertiesGradientDescent

(

)

Default constructor.

Referenced by clone().

Here is the caller graph for this function:

WeightOptimizerCommonPropertiesGradientDescent() [2/2]

nest::WeightOptimizerCommonPropertiesGradientDescent::WeightOptimizerCommonPropertiesGradientDescent ( const WeightOptimizerCommonPropertiesGradientDescent &  )

default

Copy constructor.

Member Function Documentation

clone()

WeightOptimizerCommonProperties * nest::WeightOptimizerCommonPropertiesGradientDescent::clone ( ) const

overridevirtual

Clone constructor.

Implements nest::WeightOptimizerCommonProperties.

References WeightOptimizerCommonPropertiesGradientDescent().

Here is the call graph for this function:

get_name()

std::string nest::WeightOptimizerCommonPropertiesGradientDescent::get_name ( ) const

inlineoverridevirtual

Get optimizer name.

Implements nest::WeightOptimizerCommonProperties.

get_optimizer()

WeightOptimizer * nest::WeightOptimizerCommonPropertiesGradientDescent::get_optimizer ( ) const

overridevirtual

Get optimizer.

Implements nest::WeightOptimizerCommonProperties.

References WeightOptimizerGradientDescent.

operator=()

WeightOptimizerCommonPropertiesGradientDescent & nest::WeightOptimizerCommonPropertiesGradientDescent::operator= ( const WeightOptimizerCommonPropertiesGradientDescent &  )

delete

Assignment operator.

Friends And Related Symbol Documentation

WeightOptimizerGradientDescent

friend class WeightOptimizerGradientDescent

friend

Friend class for gradient descent weight optimizer model.

Referenced by get_optimizer().

---

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

• weight_optimizer.h
• weight_optimizer.cpp