Find out how to access preview-only content
Volume 3559 of the series Lecture Notes in Computer Science pp 264-278
A New Perspective on an Old Perceptron Algorithm
- Shai Shalev-ShwartzAffiliated withSchool of Computer Sci. & Eng., The Hebrew UniversityGoogle Inc.
- , Yoram SingerAffiliated withSchool of Computer Sci. & Eng., The Hebrew UniversityGoogle Inc.
Abstract
We present a generalization of the Perceptron algorithm. The new algorithm performs a Perceptron-style update whenever the margin of an example is smaller than a predefined value. We derive worst case mistake bounds for our algorithm. As a byproduct we obtain a new mistake bound for the Perceptron algorithm in the inseparable case. We describe a multiclass extension of the algorithm. This extension is used in an experimental evaluation in which we compare the proposed algorithm to the Perceptron algorithm.
- Title
- A New Perspective on an Old Perceptron Algorithm
- Book Title
- Learning Theory
- Book Subtitle
- 18th Annual Conference on Learning Theory, COLT 2005, Bertinoro, Italy, June 27-30, 2005. Proceedings
- Pages
- pp 264-278
- Copyright
- 2005
- DOI
- 10.1007/11503415_18
- Print ISBN
- 978-3-540-26556-6
- Online ISBN
- 978-3-540-31892-7
- Series Title
- Lecture Notes in Computer Science
- Series Volume
- 3559
- Series ISSN
- 0302-9743
- Publisher
- Springer Berlin Heidelberg
- Copyright Holder
- Springer-Verlag Berlin Heidelberg
- Additional Links
- Topics
- Industry Sectors
- eBook Packages
- Editors
-
- Peter Auer (18)
- Ron Meir (19)
- Editor Affiliations
-
- 18. University of Leoben
- 19. Department of Electrical Engineering, Technion
- Authors
-
- Shai Shalev-Shwartz (20) (21)
- Yoram Singer (20) (21)
- Author Affiliations
-
- 20. School of Computer Sci. & Eng., The Hebrew University, Jerusalem, 91904, Israel
- 21. Google Inc., 1600 Amphitheater Parkway, Mountain View, CA, 94043, USA
Continue reading...
To view the rest of this content please follow the download PDF link above.