---

Algorithm Class Reference

#include <algorithm.h>

Inheritance diagram for Algorithm:

List of all members.

---

Detailed Description

Base class of all learning algorithms that calculate the readout's output. Algorithms take the filtered and preprocessed input of a readout and calculate one single output. The current algorithm interface is designed for offline-training only, i.e. all learning must occur externally. The algorithm object only "learns" through imported parameter vectors.

Public Member Functions

• Algorithm (unsigned int in_rows=1, double lower_bound=0, double upper_bound=1)
• virtual int advance (void)

  Dummy implementation.
  
  

• virtual int addIncoming (Advancable *Incoming)

  This method will be called if object Incoming wants to send information to this object.
  
  

• virtual int addOutgoing (Advancable *Outgoing)

  This method will be called if this object wants to send information to object Outgoing.
  
  

• virtual void setParameter (string name, double value)
• virtual double getParameter (string name)
• virtual list< string > validParameters (void)
• virtual int apply (const double *S, double *X)=0
• virtual void reset ()
• virtual int importRepresentation (const double *rep, int rep_length)=0
• virtual double * exportRepresentation (int *rep_length)=0
• int getInputRows ()
• void getRange (double *a, double *b)
• void setRange (double a, double b)
• virtual string getFormatDescription ()=0
• virtual int updateInternal ()

Public Attributes

• double range_low

  Lower bound of algorithms range.
  
  

• double range_high

  Upper bound of algorithms range.
  
  

Protected Attributes

• map< string, double * > params

  A map storing pointers to the parameters.
  
  

• int nInputRows

  Number of rows for input vectors.
  
  

• double dInputRows

  Dummy for parameter setting.
  
  

---

Constructor & Destructor Documentation

Algorithm::Algorithm (  unsigned int    in_rows = 1, double    lower_bound = 0, double    upper_bound = 1 )

Constructs a new learning algorithm. Parameters: in_rows  Number of rows in each input vector. lower_bound  Lower bound of the algorithms range. upper_bound  Upper bound of the algorithms range.

---

Member Function Documentation

virtual int Algorithm::apply (  const double *    S, double *    X )  [pure virtual]

Applies the currently learned function to the filtered and preprocessed input vector. Parameters: S  State of the liquid (= filtered and preprocessed response of the neural microcircuit). X  Target pointer where to save the result. Returns: -1 if an error occured, 1 for success. Implemented in linear_classification, and linear_regression.

virtual double* Algorithm::exportRepresentation (  int *    rep_length )  [pure virtual]

Exports the representation of this algorithm for use in external objects. Parameters: rep_length  Length of the representation vector. Returns: A list of parameters that represent the algorithm. Warning: Do not forget to free the memory reserved for the representation! Implemented in linear_classification, and linear_regression.

virtual string Algorithm::getFormatDescription (    )  [pure virtual]

Returns a textual description of the representation format for import/export - Representation. Implemented in linear_classification, and linear_regression.

int Algorithm::getInputRows (    )  [inline]

Returns the number of input rows.

double Algorithm::getParameter (  string    name )  [virtual]

Returns the current value of a parameter. Parameters: name  Name of the parameter. Returns: The value of the parameter.

void Algorithm::getRange (  double *    a, double *    b )

Returns the range of the algorithm's target values [a, b]. Parameters: a  Address of lower bound for algorithm's target values. b  Address of upper bound for algorithm's target values.

virtual int Algorithm::importRepresentation (  const double *    rep, int    rep_length )  [pure virtual]

Imports the data from an externally (e.g. Matlab) trained algorithm. Parameters: rep  Representation of the algorithm as a double vector. rep_length  Length of the representation vector. Returns: -1 if an error occured, 1 for success. Implemented in linear_classification, and linear_regression.

virtual void Algorithm::reset (  void    )  [inline, virtual]

Resets the information stored within the algorithm. Implements Advancable. Reimplemented in linear_classification, and linear_regression.

void Algorithm::setParameter (  string    name, double    value )  [virtual]

Sets a parameter of the algorithm. Parameters: name  Name of the parameter. value  Value to set for the parameter.

void Algorithm::setRange (  double    a, double    b )

Sets the range of the algorithm's target values [a, b]. Parameters: a  Lower bound for algorithm's target values. b  Upper bound for algorithm's target values.

int Algorithm::updateInternal (    )  [virtual]

This function is called after parameters are updated.

list< string > Algorithm::validParameters (  void    )  [virtual]

Returns the names of the valid parameters. Returns: A string list indicating the valid parameter names.

---