OrgLion-ML
/
dlib
mirror of https://github.com/davisking/dlib.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Added some comments to clarify what exactly is a valid loss function. 

--HG--
extra : convert_revision : svn%3Afdd8eb12-d10e-0410-9acb-85c331704f74/trunk%404236
This commit is contained in:
Davis King 2011-04-29 13:29:46 +00:00
parent 4bc0186443
commit b7594d82e7
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
dlib/svm/structural_svm_problem_abstract.h
View File

@ -51,7 +51,8 @@ namespace dlib
- let PSI(x,y) == the joint feature vector for input x and a label y. - let PSI(x,y) == the joint feature vector for input x and a label y.
- let F(x,y|w) == dot(w,PSI(x,y)). - let F(x,y|w) == dot(w,PSI(x,y)).
- let LOSS(idx,y) == the loss incurred for predicting that the ith-th training - let LOSS(idx,y) == the loss incurred for predicting that the ith-th training
sample has a label of y. sample has a label of y. Note that LOSS() should always be >= 0 and should
become exactly 0 when y is the correct label for the idx-th sample.
- let x_i == the i-th training sample. - let x_i == the i-th training sample.
- let y_i == the correct label for the i-th training sample. - let y_i == the correct label for the i-th training sample.
- The number of data samples is N. - The number of data samples is N.
@ -205,7 +206,8 @@ namespace dlib
- let PSI(X,y) == the joint feature vector for input X and an arbitrary label y. - let PSI(X,y) == the joint feature vector for input X and an arbitrary label y.
- let F(X,y) == dot(current_solution,PSI(X,y)). - let F(X,y) == dot(current_solution,PSI(X,y)).
- let LOSS(idx,y) == the loss incurred for predicting that the ith-th sample - let LOSS(idx,y) == the loss incurred for predicting that the ith-th sample
has a label of y. has a label of y. Note that LOSS() should always be >= 0 and should
become exactly 0 when y is the correct label for the idx-th sample.
Then the separation oracle finds a Y such that: Then the separation oracle finds a Y such that:
Y = argmax over all y: LOSS(idx,y) + F(X,y) Y = argmax over all y: LOSS(idx,y) + F(X,y)