Share Email Print

Proceedings Paper

Capability measures of artificial neural network architectures based on soft shattering
Author(s): Mark E. Oxley; Martha Alvey Carter
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 21 March 2001
PDF: 9 pages
Proc. SPIE 4390, Applications and Science of Computational Intelligence IV, (21 March 2001); doi: 10.1117/12.421183
Show Author Affiliations
Mark E. Oxley, Air Force Institute of Technology (United States)
Martha Alvey Carter, National Air Intelligence Ctr. (United States)

Published in SPIE Proceedings Vol. 4390:
Applications and Science of Computational Intelligence IV
Kevin L. Priddy; Paul E. Keller; Peter J. Angeline, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?