Journal article
Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
- Abstract:
-
We introduce a new method for proving explicit upper bounds on the VC dimension of general functional basis networks and prove as an application, for the first time, that the VC dimension of analog neural networks with the sigmoidal activation function σ(y)=1/1+e−y is bounded by a quadratic polynomial O((lm)2) in both the number l of programmable parameters, and the number m of nodes. The proof method of this paper generalizes to much wider class of Pfaffian activation functions and formulas and gives also for the first time polynomial bounds on their VC dimension. We present also some other applications of our method.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, pdf, 438.4KB, Terms of use)
-
- Publisher copy:
- 10.1006/jcss.1997.1477
+ Engineering and Physical Sciences Research Council
More from this funder
- Funding agency for:
- Macintyre, A
- Publisher:
- Elsevier
- Journal:
- Journal of Computer and System Sciences More from this journal
- Volume:
- 54
- Issue:
- 1
- Pages:
- 169-176
- Publication date:
- 1997-02-01
- Edition:
- Publisher's version
- DOI:
- ISSN:
-
0022-0000
- Language:
-
English
- Subjects:
- UUID:
-
uuid:a14465ce-11d9-4f89-aeec-fcf0bea603ed
- Local pid:
-
ora:8782
- Deposit date:
-
2014-07-15
Terms of use
- Copyright holder:
- Academic Press
- Copyright date:
- 1997
- Notes:
- Copyright 1997 Academic Press. Published by Elsevier B.V. All rights reserved. Re-use of this article is permitted in accordance with the Terms and Conditions set out at http://www.elsevier.com/open-access/userlicense/1.0/
- Licence:
- Other
If you are the owner of this record, you can report an update to it here: Report update to this record