CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 4390 > Article
Paper
21 March 2001 Capability measures of artificial neural network architectures based on soft shattering
Mark E. Oxley, Martha Alvey Carter
Author Affiliations +
Proceedings Volume 4390, Applications and Science of Computational Intelligence IV; (2001) https://doi.org/10.1117/12.421183
Event: Aerospace/Defense Sensing, Simulation, and Controls, 2001, Orlando, FL, United States
Abstract
Measures of an artificial neural network ANN capability are typically based on the Vapnik-Chernonvekis dimension and its variations. These measures may be underestimating the actual ANN's capabilities and hence overestimating the required number of examples for learning. This is caused by relying on a single invariant description of the problem set, which, in this case is cardinality, and requiring worst case geometric arrangements and colorings. A capability measure of an ANN is usually related to the desired characteristics of the problem sets. The mathematical framework has been established in which to express other desired invariant descriptors of a capability measure e.g., V-C dimension uses cardinality. A new invariant is defined on the problem space that softens the hard shattering constraint and yields a new capability measure of ANN's. The theory is given as well as examples that demonstrate this new measure.
© (2001) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Mark E. Oxley and Martha Alvey Carter "Capability measures of artificial neural network architectures based on soft shattering", Proc. SPIE 4390, Applications and Science of Computational Intelligence IV, (21 March 2001); https://doi.org/10.1117/12.421183
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 9 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Artificial neural networks
Silicon
Astatine
Mathematics
Network architectures
Radon
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top