Prior Knowledge in Support Vector Kernels

Schölkopf, Bernhard, Simard, Patrice, Smola, Alex J., Vapnik, Vladimir

–Neural Information Processing Systems 

We explore methods for incorporating prior knowledge about a problem at hand in Support Vector learning machines. We show that both invariances undergroup transfonnations and prior knowledge about locality in images can be incorporated by constructing appropriate kernel functions.

Neural Information Processing Systems

Dec-31-1998

Conferences    PDF

Add feedback

Duplicate Docs Excel Report

Title
Prior Knowledge in Support Vector Kernels
Prior Knowledge in Support Vector Kernels

Similar Docs  Excel Report  more

TitleSimilaritySource
None found