auryn::EulerTrace Class Reference

Solves a set of identical linear differential equations with the Euler method. It is used to implement synaptic traces in most STDP models. More...

#include <EulerTrace.h>

Inheritance diagram for auryn::EulerTrace:

Collaboration diagram for auryn::EulerTrace:

Public Member Functions
	EulerTrace (NeuronID n, AurynFloat timeconstant)
virtual	~EulerTrace ()
void	evolve ()
void	set_timeconstant (AurynFloat timeconstant)
void	set_target (AurynStateVector *target)
void	follow ()
Public Member Functions inherited from auryn::Trace
	Trace (NeuronID n, AurynFloat timeconstant)
	Default constructor. More...
virtual	~Trace ()
	Default destructor. More...
virtual void	inc (NeuronID i)
	Increment given trace by 1. More...
virtual void	inc (SpikeContainer *sc)
	Increment given traces by 1. More...
AurynFloat	get_tau ()
	Get decay time constant. More...
virtual AurynFloat	normalized_get (NeuronID i)
	Get trace value of trace dived by tau. More...
virtual AurynStateVector *	get_state_ptr ()
	Get pointer to state AurynStateVector for fast processing. More...
virtual void	follow (AurynVectorFloat *v, const float rate)
	Follow other vector. More...
Public Member Functions inherited from auryn::AurynVectorFloat
	AurynVectorFloat (NeuronID n)
	Default constructor. More...
	~AurynVectorFloat ()
	Default destructor. More...
virtual void	resize (NeuronID new_size)
	resize data array to new_size More...
void	scale (const float a)
void	saxpy (const float a, AurynVectorFloat *x)
void	clip (const float min, const float max)
void	add (const float c)
void	add (AurynVectorFloat *v)
void	sum (AurynVectorFloat *a, AurynVectorFloat *b)
void	sum (AurynVectorFloat *a, const float b)
void	mul (const float a)
void	mul (AurynVectorFloat *v)
void	diff (AurynVectorFloat *a, AurynVectorFloat *b)
void	diff (AurynVectorFloat *a, const float b)
void	diff (const float a, AurynVectorFloat *b)
void	follow (AurynVectorFloat *v, const float rate)
Public Member Functions inherited from auryn::AurynVector< float, NeuronID >
	AurynVector (NeuronID n)
	Default constructor. More...
	AurynVector (AurynVector *vec)
	Copy constructor. More...
virtual	~AurynVector ()
	Default destructor. More...
void	copy (AurynVector *v)
	Copies vector v. More...
float	get (NeuronID i)
	Gets element i from vector. More...
float *	ptr (NeuronID i=0)
	Gets pointer to element i from vector. More...
void	set (NeuronID i, float value)
	Sets element i in vector to value. More...
void	set_all (const float v)
	Set all elements to value v. More...
void	set_zero ()
	Set all elements to zero. More...
void	scale (const float a)
	Scales all vector elements by a. More...
void	add (const float c)
	Adds constant c to each vector element. More...
void	add (AurynVector *v)
	Adds a vector v to the vector. More...
void	add_specific (const NeuronID i, const float c)
	Adds the value c to specific vector element i. More...
void	mul_specific (const NeuronID i, const float c)
	Multiply to specific vector element with data index i with the constant c. More...
void	sub (const float c)
	Subtract constant c to each vector element. More...
void	sub (AurynVector *v)
	Elementwise subtraction. More...
void	mul (const float a)
	Multiply all vector elements by constant. More...
void	mul (AurynVector *v)
	Element-wise vector multiply. More...
void	div (const float a)
	Element-wise division. More...
void	div (AurynVector *v)
	Element-wise vector division. More...
void	div (AurynVector *a, AurynVector *b)
	Element-wise vector division which stores the result in this. More...
void	saxpy (const float a, AurynVector *x)
	SAXPY operation as in GSL. More...
void	follow (AurynVector< float, NeuronID > *v, const float rate)
	Follows target vector v with rate. More...
void	follow_scalar (const float a, const float rate)
	Like follow but with a scalar target value a. More...
void	elementwise_max (AurynVector *v1, AurynVector *v2)
	Elementwise max operation. More...
void	elementwise_max (AurynVector *v1)
	Elementwise max operation with another vector. More...
void	pow (const unsigned int n)
	Takes each element to the n-th power. More...
void	fast_exp ()
	Computes an approximation of exp(x) for each vector element. More...
void	exp ()
	Computes exp(x) for each vector element. More...
void	sigmoid (AurynVector *x, const float beta, const float thr)
	Computes sigmoid(beta*(x-thr)) for each vector element and stores result in this instance. More...
void	sqrt ()
	Takes the square root of each element. More...
void	neg ()
	Flips the sign of all elements. More...
void	inv ()
	Computes 1./x of each element. More...
void	sum (AurynVector *a, AurynVector *b)
	Computes the sum a+b and stores the result in this instance. More...
void	sum (AurynVector *a, const float b)
	Computes the sum a+b and stores the result in this instance. More...
void	diff (AurynVector *a, AurynVector *b)
	Computes the difference a-b and stores the result in this instance. More...
void	diff (AurynVector *a, const float b)
	Computes the difference a-b and stores the result in this instance. More...
void	diff (const float a, AurynVector *b)
	Computes the difference a-b and stores the result in this instance. More...
void	sqr ()
	Squares each element. More...
void	abs ()
	Takes absolute value of each element. More...
void	rect ()
	Rectifies all elements. More...
void	neg_rect ()
	Negatively rectifies all elements. More...
void	clip (float min, float max)
	Clips all vector elements to the range min max. More...
double	var ()
	Computes the variance of the vector elements on this rank. More...
double	std ()
	Computes the standard deviation of all elements on this rank. More...
double	mean ()
	Computes the mean of the vector elements on this rank. More...
double	element_sum ()
	Computes the sum of the vector elements. More...
double	l1norm ()
	Computes the l1 norm of the vector. More...
double	l2norm ()
	Computes the l2 norm of the vector. More...
double	max ()
	Returns the max of the vector elements. More...
double	min ()
	Returns the min of the vector elements. More...
NeuronID	nonzero ()
	Computes number of nonzero elements on this rank. More...
void	zero_effective_zeros (const float epsilon=1e-3)
	Sets all values whose absolute value is smaller than epsilon to zero. More...
void	add_random_normal (AurynState mean=0.0, AurynState sigma=1.0, unsigned int seed=8721)
void	set_random_normal (AurynState mean=0.0, AurynState sigma=1.0, unsigned int seed=8721)
void	set_random (unsigned int seed=0)
	Initializes vector elements with Gaussian of unit varince and a seed derived from system time if no seed or seed of 0 is given. More...
bool	any ()
	Returns true if any element is nonzero. More...
bool	any (float eps)
	Returns true if any element is nonzero. More...
void	print ()
	Print vector elements to stdout for debugging. More...
void	write_to_file (std::string filename)
	Print vector elements to a text file for debugging. More...

Additional Inherited Members
Public Attributes inherited from auryn::AurynVector< float, NeuronID >
NeuronID	size
	Size of the vector. More...
float *	data
	Pointer to the array housing the data. More...
Protected Member Functions inherited from auryn::AurynVector< float, NeuronID >
void	check_size (NeuronID x)
	Checks if argument is larger than size and throws and exception if so. More...
void	check_size (AurynVector *v)
	Checks if vector size matches to this instance. More...
void	allocate (const NeuronID n)
	Implements aligned memory allocation. More...
void	freebuf ()
float	fast_exp256 (float x)
	Computes approximation of exp(x) via fast series approximation up to n=256. More...
Protected Attributes inherited from auryn::Trace
AurynFloat	tau

Detailed Description

Solves a set of identical linear differential equations with the Euler method. It is used to implement synaptic traces in most STDP models.

This solver simultaneoulsy computes linear traces (mostly to implement synapses) using Euler's method. Another solver is readily available within the Auryn framework. The LinearTrace objects solves the same problem but using the analytic solution. This results in less updates. However - so far it turned out to be inferior in performance to the EulerTrace.

Constructor & Destructor Documentation

EulerTrace()

EulerTrace::EulerTrace	(	NeuronID	n,
		AurynFloat	timeconstant
	)

Default constructor

                                                          : Trace( calculate_vector_size(n), timeconstant )
{
        init(n,timeconstant);
}

~EulerTrace()

EulerTrace::~EulerTrace ( )

virtual

Default destructor

{
        free();
}

Member Function Documentation

evolve()

void EulerTrace::evolve ( )

virtual

Perform Euler step.

Implements auryn::Trace.

Reimplemented in auryn::LinearTrace.

{
        scale(scale_const);
}

Here is the call graph for this function:

follow()

void EulerTrace::follow ( )

virtual

Perform Euler step but follow target vector instead of zero-decay

Implements auryn::Trace.

{ 
        super::follow(target_ptr, mul_follow);
}

Here is the call graph for this function:

set_target()

void EulerTrace::set_target ( AurynStateVector *  target )

virtual

set the target vector for follow operation

Implements auryn::Trace.

{
        if ( target != NULL ) {
                target_ptr = target ;
                copy(target);
        }
}

Here is the call graph for this function:

set_timeconstant()

void EulerTrace::set_timeconstant ( AurynFloat  timeconstant )

virtual

Set the time constant of the trace

Reimplemented from auryn::Trace.

{
        super::set_timeconstant(timeconstant);
        mul_follow = auryn_timestep/tau;
        scale_const = std::exp(-auryn_timestep/tau);
}

Here is the call graph for this function:

---

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

• /home/zenke/auryn/src/auryn/EulerTrace.h
• /home/zenke/auryn/src/auryn/EulerTrace.cpp