Incorporating Invariances in Support Vector Learning Machines

Incorporating Invariances in Support Vector Learning Machines (1996)

Cached

Download Links

[www.kernel-machines.org]
[svm.research.bell-labs.com]

Other Repositories/Bibliography

DBLP

by Bernhard Schölkopf , Chris Burges , Vladimir Vapnik

Citations:

61 - 11 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Incorporating Invariances in Support Vector Learning Machines	user correction - Legacy Corrections
AUTHOR NAME	Bernhard Schölkopf	user correction - Legacy Corrections
AUTHOR ADDR	12	user correction - Legacy Corrections
AUTHOR NAME	Chris Burges	user correction - Legacy Corrections
AUTHOR AFFIL	2	user correction - Legacy Corrections
AUTHOR NAME	Vladimir Vapnik	user correction - Legacy Corrections
AUTHOR AFFIL	; 2; 1; Max--Planck--Institut fur biologische Kybernetik,; 2; AT&T Bell Laboratories, Holmdel	user correction - Legacy Corrections
AUTHOR ADDR	; Tubingen, Germany, E--mail; NJ, USA	user correction - Legacy Corrections
ABSTRACT	. Developed only recently, support vector learning machines achieve high generalization ability by minimizing a bound on the expected test error; however, so far there existed no way of adding knowledge about invariances of a classification problem at hand. We present a method of incorporating prior knowledge about transformation invariances by applying transformations to support vectors, the training examples most critical for determining the classification boundary. 1 Incorporating Invariances in: C. von der Malsburg, W. von Seelen, J. C. Vorbruggen, & B. Sendhoff (eds.): Artificial Neural Networks --- ICANN'96. Springer Lecture Notes in Computer Science, Vol. 1112, Berlin, 1996, 47 --52 In many applications of learning procedures, prior knowledge about properties of the function to be learned is available (for a review, see Abu--Mostafa, 1995). For instance, certain transformations of the input could be known to leave function values unchanged. Mostly, two different ways of exploit...	user correction - Legacy Corrections
YEAR	1996	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	47--52	INFERENCE
VOLUME	1112	INFERENCE
CITATIONS	2 found	ParsCit 1.0