Published April 25, 2001
| Submitted
Report
Open
Similar Classifiers and VC Error Bounds
- Creators
- Bax, Eric
Abstract
We improve error bounds based on VC analysis for classes with sets of similar classifiers. We apply the new error bounds to separating planes and artificial neural networks.
Additional Information
© 1997 California Institute of Technology.Attached Files
Submitted - CSTR1997.pdf
Submitted - postscript.ps
Files
CSTR1997.pdf
Files
(542.6 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:a24d9c69b0fa4e4ec9230b2e3ce3369d
|
188.1 kB | Preview Download |
|
md5:63cda266d84bac29f4bb3e57ccbd6726
|
354.5 kB | Download |
Additional details
- Eprint ID
- 26815
- Resolver ID
- CaltechCSTR:1997.cs-tr-97-14
- Created
-
2001-04-25Created from EPrint's datestamp field
- Updated
-
2019-10-03Created from EPrint's last_modified field
- Caltech groups
- Computer Science Technical Reports