Share Email Print

Proceedings Paper

Generalized measures of artificial neural network capabilities
Author(s): Martha Alvey Carter; Mark E. Oxley
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Current measures of an artificial neural networks (ANN) capability are the V-C dimension and its variations. These measures may be underestimating capabilities (in the primal sense) and hence overestimating the required number of examples for learning (in the dual sense). This is a result of relying on a single invariant description of the problem set, which is cardinality, and requiring worst case geometries and colorings. Generalization of a capability measure allows aligning the measure with desired characteristics of the problem sets. We present a mathematical framework in which to express other desired invariant descriptors of a capability measure, and guarantee proper application of the measure to ANNs. We define a collection of invariants defined on the problem space that yield new capability measures of ANNs. A specific example of an invariant is given which is based on geometric complexity of the problem set and yields a new measure of ANNs called the Ox-Cart dimension.

Paper Details

Date Published: 22 March 1999
PDF: 12 pages
Proc. SPIE 3722, Applications and Science of Computational Intelligence II, (22 March 1999); doi: 10.1117/12.342875
Show Author Affiliations
Martha Alvey Carter, National Air Intelligence Ctr. (United States)
Mark E. Oxley, Air Force Institute of Technology (United States)

Published in SPIE Proceedings Vol. 3722:
Applications and Science of Computational Intelligence II
Kevin L. Priddy; Paul E. Keller; David B. Fogel; James C. Bezdek, Editor(s)

© SPIE. Terms of Use
Back to Top