Guaranteed two-pass convergence for supervised and inferential learning

Author

Healy, Michael J. ; Caudell, Thomas P.

Author_Institution

Dept. of Electr. & Comput. Eng., New Mexico Univ., Albuquerque, NM, USA

Volume

9

Issue

1

fYear

1998

fDate

1/1/1998 12:00:00 AM

Firstpage

195

Lastpage

204

Abstract

We present a theoretical analysis of a version of the LAPART adaptive inferencing neural network. Our main result is a proof that the new architecture, called LAPART 2, converges in two passes through a fixed training set of inputs. We also prove that it does not suffer from template proliferation. For comparison, Georgiopoulos et al. (1994) have proved the upper bound n-1 on the number of passes required for convergence for the ARTMAP architecture, where n is the size of the binary pattern input space. If the ARTMAP result is regarded as an n-pass, or finite-pass, convergence result, ours is then a two-pass, or fixed-pass, convergence result. Our results have added significance in that they apply to set-valued mappings, as opposed to the usual supervised learning model of affixing labels to classes

Keywords

ART neural nets; convergence; inference mechanisms; learning (artificial intelligence); neural net architecture; pattern classification; LAPART 2; LAPART adaptive inferencing neural network; binary pattern input space; fixed-pass convergence; inferential learning; set-valued mappings; supervised learning; two-pass convergence; Adaptive systems; Convergence; Data mining; Data preprocessing; Logic testing; Neural networks; Resonance; Subspace constraints; Supervised learning; Upper bound;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.655041

Filename

655041