#include <recencyPredictor.h>

Inheritance diagram for RecencyPredictor:

Collaboration diagram for RecencyPredictor:

Public Member Functions
	RecencyPredictor (Configuration , ContextTracker , const char *)

	~RecencyPredictor ()

virtual Prediction	predict (const size_t size, const char **filter) const
	Generate prediction. More...

virtual void	learn (const std::vector< std::string > &change)

virtual void	update (const Observable *variable)

Public Member Functions inherited from Predictor
	Predictor (Configuration configuration, ContextTracker contextTracker, const char predictorName="Predictor", const char shortDescription="", const char *longDescription="")

virtual	~Predictor ()

const std::string	getName () const

const std::string	getShortDescription () const

const std::string	getLongDescription () const

Public Member Functions inherited from Observer
virtual	~Observer ()

Private Member Functions
void	set_lambda (const std::string &value)

void	set_n_0 (const std::string &value)

void	set_cutoff_threshold (const std::string &value)

Private Attributes
std::string	LOGGER

std::string	LAMBDA

std::string	N_0

std::string	CUTOFF_THRESHOLD

double	lambda

double	n_0

size_t	cutoff_threshold

Dispatcher< RecencyPredictor >	dispatcher

Additional Inherited Members
Protected Member Functions inherited from Predictor
virtual bool	token_satisfies_filter (const std::string &token, const std::string &prefix, const char **filter) const

virtual void	set_logger (const std::string &level)

Protected Member Functions inherited from Observer
	Observer ()

Protected Attributes inherited from Predictor
const std::string	name

const std::string	shortDescription

const std::string	longDescription

const std::string	PREDICTORS

ContextTracker *	contextTracker

Configuration *	configuration

Logger< char >	logger

Detailed Description

Recency predictor, a recency promotion statistical predictor.

RecencyPredictor, based on recency promotion principle, generates predictions by assigning exponentially decaying probability values to previously encountered tokens. Tokens are assigned a probability value that decays exponentially with their distance from the current token, thereby promoting context recency

(from Wikipedia) A quantity is said to be subject to exponential decay if it decreases at a rate proportional to its value. Symbolically, this can be expressed as the following differential equation, where N is the quantity and λ is a positive number called the decay constant.

frac{dN}{dt} = -lambda N.

The solution to this equation is below:

N(t) = N_0 e^{-lambda t}

Here N(t) is the quantity at time t, and N0 = N(0) is the (initial) quantity, at time t = 0.

This is the form of the equation that is most commonly used to describe exponential decay. The constant of integration N0 denotes the original quantity at t = 0. (The notation λ for the decay constant is a remnant of the usual notation for an eigenvalue. In this case, λ is the eigenvalue of the opposite of the differentiation operator with N(t) as the corresponding eigenfunction).

Definition at line 64 of file recencyPredictor.h.