10.5.3. Transductive Support Vector Machines
According to the inductive inference philosophy, one starts from the particular knowledge (training set using labeled data) and then the general rule (the classifier or regressor) is derived, which is subsequently used to predict the labels of specific points comprising the test set. In other words, one follows a path
Vapnik and Chervonenkis, pushing the frontiers, questioned whether this is indeed the best path to follow in practice. In cases where the training data set is limited in size, deriving a good general rule becomes a hard task. For such cases, they proposed the transductive inference ...
Get Pattern Recognition, 4th Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
