class SVMRegression

SVM in regression.

Inheritance:

Public Methods
SVMRegression(Kernel* kernel_, real* C_=NULL, IOSequenceArray* io_sequence_array_=NULL)

Inherited from SVM:

Public Fields
Allocator* sv_allocator
IOSequenceArray* io_sequence_array
DataSet* data
Kernel* kernel
real b
int* support_vectors
real* sv_alpha
Sequence** sv_sequences
int n_support_vectors
int n_support_vectors_bound

Public Methods
bool bCompute()

Inherited from QCMachine:

Public Fields
real* Cup
real* Cdown
real bound_eps
int n_alpha
real* alpha
real* grad
real* y
QCCache* cache

Public Methods
virtual void checkSupportVectors()

Inherited from Machine:

Public Fields
Sequence* outputs

Public Methods
virtual void forward(Sequence* sequence)
virtual void reset()
virtual void setDataSet(DataSet* dataset_)

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)
virtual void loadXFile(XFile* file)
virtual void saveXFile(XFile* file)
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

SVM in regression.
Try to find the hyperplane f(x) = w.x+b as minimize
(where if , else ) (and is the number of training examples) (the size of is here 2*)
("eps" is eps_regression in the code)
(in fact, we use a kernel kernel instead of a dot product)
The coefficients are given by C_ when you call the constructor. If this one is NULL, all C_j will have the value given by the "C" option. (The size of C_ must be 2*data->n_real_examples)
Options:

"C" real trade off between the weight decay and the error [100]
"eps regression" real size of the error tube [0.7]
"cache size" real cache size (in Mo) [50]