A complexity estimation approach for estimating neural net size

Author

Kim, Kyung K. ; Manry, Michael T.

Author_Institution

Lockheed Martin Tactical Aircraft Syst., Fort Worth, TX, USA

Volume

2

fYear

1995

fDate

Oct. 30 1995-Nov. 1 1995

Firstpage

899

Abstract

A complexity estimation technique is developed for predicting the number of hidden units a multilayer perceptron (MLP) requires to reach a given performance. First, a distance measure is developed which rejects useless inputs. An approximately optimal clustering algorithm for designing nearest neighbor estimators (NNEs) is presented which uses the distance measure. New formulas are given for the numbers of hidden units required to store a given number of patterns. Examples are given which illustrate the usefulness of this technique.

Keywords

multilayer perceptrons; approximately optimal clustering algorithm; complexity estimation; distance measure; hidden units; multilayer perceptron; nearest neighbor estimators; neural net size estimation; Aircraft propulsion; Algorithm design and analysis; Clustering algorithms; Filters; Iterative algorithms; Multilayer perceptrons; Nearest neighbor searches; Neural networks; Piecewise linear approximation; Postal services;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 1995. 1995 Conference Record of the Twenty-Ninth Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-8186-7370-2

Type

conf

DOI

10.1109/ACSSC.1995.540830

Filename

540830