class QCTrainer

Train a QCMachine.

Inheritance:

Public Methods

QCTrainer(QCMachine* qcmachine_)

void train(DataSet* data, MeasurerList* measurers)

Train it.

Inherited from Trainer:

Public Methods

virtual void test(MeasurerList* measurers)

static Allocator* extractMeasurers(MeasurerList* measurers, DataSet* train, DataSet*** datas, Measurer**** meas, int** n_meas, int* n_datas)

virtual void loadXFile(XFile* file)

virtual void saveXFile(XFile* file)

Inherited from Object:

Public Fields

Allocator* allocator

Public Methods

void addOption(const char* name, int size, void* ptr, const char* help="")

void addIOption(const char* name, int* ptr, int init_value, const char* help="")

void addROption(const char* name, real* ptr, real init_value, const char* help="")

void addBOption(const char* name, bool* ptr, bool init_value, const char* help="")

void addOOption(const char* name, Object** ptr, Object* init_value, const char* help="")

void setOption(const char* name, void* ptr)

void setIOption(const char* name, int option)

void setROption(const char* name, real option)

void setBOption(const char* name, bool option)

void setOOption(const char* name, Object* option)

void load(const char* filename)

void save(const char* filename)

void* operator new(size_t size, Allocator* allocator_=NULL)

void* operator new(size_t size, Allocator* allocator_, void* ptr_)

void operator delete(void* ptr)

Documentation

Train a QCMachine. With the conventions of QCMachine.h, Q is given by the class QCCache (in cache)

Options:

"unshrink"	bool	unshrink or not unshrink	[false]
"max unshrink"	int	maximal number of unshrinking	[1]
"iter shrink"	int	minimal number of iterations to shrink	[100]
"eps shrink"	real	shrinking accuracy	[1E-4 (f) 1E-9 (d)]
"end accuracy"	real	end accuracy	[0.01]
"iter message"	int	number of iterations between messages	[1000]

Note: "iter shrink" must be carefully chosen. Read http://www.ai.mit.edu/projects/jmlr/papers/volume1/collobert01a/collobert01a.ps.gz for more details.

QCTrainer(QCMachine* qcmachine_)

void train(DataSet* data, MeasurerList* measurers)

Train it. Before calling this function, grad in qcmachine must contain the gradient of QP(alpha) with respect to alpha = 0.

( = , with the conventions of QCMachine.h)

Moreover alpha in qcmachine has to be zero.

This class has no child classes.

Author:

Ronan Collobert (collober@idiap.ch)

See Also:

QCCache
QCMachine

Alphabetic index HTML hierarchy of classes or Java