BayesOpt
bayesopt::ARDkernel Class Reference

Abstract class for anisotropic kernel functors using ARD (Automatic Relevance Determination) More...

#include <kernel_atomic.hpp>

+ Inheritance diagram for bayesopt::ARDkernel:
+ Collaboration diagram for bayesopt::ARDkernel:

Protected Member Functions

double computeWeightedNorm2 (const vectord &x1, const vectord &x2)
 

Additional Inherited Members

- Public Member Functions inherited from bayesopt::AtomicKernel
virtual void init (size_t input_dim)
 
void setHyperParameters (const vectord &theta)
 
vectord getHyperParameters ()
 
size_t nHyperParameters ()
 
- Public Member Functions inherited from bayesopt::Kernel
virtual void init (size_t input_dim, Kernel *left, Kernel *right)
 
virtual double operator() (const vectord &x1, const vectord &x2)=0
 
virtual double gradient (const vectord &x1, const vectord &x2, size_t component)=0
 
- Protected Attributes inherited from bayesopt::AtomicKernel
size_t n_params
 
vectord params
 
- Protected Attributes inherited from bayesopt::Kernel
size_t n_inputs
 

Detailed Description

Abstract class for anisotropic kernel functors using ARD (Automatic Relevance Determination)

Definition at line 90 of file kernel_atomic.hpp.


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