Journal article icon

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 mu...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Publisher's version

Actions


Access Document


Files:
Publisher copy:
10.1006/jcss.1997.1477

Authors


More by this author
Institution:
University of Bonn
Department:
Department of Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Department:
Mathematical, Physical & Life Sciences Division - Mathematical Institute
Role:
Author
Publisher:
Elsevier Publisher's website
Journal:
Journal of Computer and System Sciences Journal website
Volume:
54
Issue:
1
Pages:
169-176
Publication date:
1997-02-05
DOI:
ISSN:
0022-0000
URN:
uuid:a14465ce-11d9-4f89-aeec-fcf0bea603ed
Local pid:
ora:8782
Language:
English
Subjects:

Terms of use


Metrics


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP