Added missing comments and fixed some existing ones.

--HG--
extra : convert_revision : svn%3Afdd8eb12-d10e-0410-9acb-85c331704f74/trunk%402230
This commit is contained in:
Davis King 2008-05-13 02:04:28 +00:00
parent 5874bcd116
commit 07140ec98d
2 changed files with 10 additions and 6 deletions

View File

@ -7,6 +7,7 @@
#include "../matrix/matrix_abstract.h"
#include "../algs.h"
#include "../serialize.h"
#include "kernel_abstract.h"
namespace dlib
{
@ -17,6 +18,9 @@ namespace dlib
class krls
{
/*!
REQUIREMENTS ON kernel_type
is a kernel function object as defined in dlib/svm/kernel_abstract.h
INITIAL VALUE
- dictionary_size() == 0

View File

@ -62,8 +62,8 @@ namespace dlib
- y(i) == -1 or +1
- y(i) is the class that should be assigned to training example x(i)
- 0 < nu < maximum_nu(y)
- kernel_function == a kernel function object type as defined at the top
of this document.
- kernel_function == a kernel function object type as defined at the
top of dlib/svm/kernel_abstract.h
ensures
- trains a nu support vector classifier given the training samples in x and
labels in y. Training is done when the error is less than eps.
@ -112,8 +112,8 @@ namespace dlib
- y(i) == -1 or +1
- y(i) is the class that should be assigned to training example x(i)
- 0 < nu < maximum_nu(y)
- kernel_function == a kernel function object type as defined at the top
of this document.
- kernel_function == a kernel function object type as defined at the
top of dlib/svm/kernel_abstract.h
ensures
- trains a nu support vector classifier given the training samples in x and
labels in y. Training is done when the error is less than eps.
@ -158,8 +158,8 @@ namespace dlib
- y(i) == -1 or +1
- y(i) is the class that should be assigned to training example x(i)
- 0 < nu < maximum_nu(y)
- kernel_function == a kernel function object type as defined at the top
of this document.
- kernel_function == a kernel function object type as defined at the
top of dlib/svm/kernel_abstract.h
ensures
- performs k-fold cross validation by training a nu-svm using the svm_nu_train()
function. Each fold is tested using the learned decision_function and the