Return the most likely label
Return the most likely label
Return the most likely label
Return the most likely label
Transforms output labels L=>M.
Transforms output labels L=>M. if f(x) is not one-to-one then the max of score from the L's are used.
For the observation, return the score for each label that has a nonzero score.
For the observation, return the score for each label that has a nonzero score.
A LinearClassifier is a multi-class classifier with decision function:
\hat y_i = \arg\max_y w_y^T x_i + b_y