Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
EFFECTS OF NORMALIZATION CONSTRAINTS ON COMPETITIVE LEARNING
Autore:
SUTTON GG; REGGIA JA;
Indirizzi:
UNIV MARYLAND,DEPT COMP SCI COLL PK MD 20742 UNIV MARYLAND,DEPT NEUROL COLL PK MD 20742 UNIV MARYLAND,INST ADV COMP STUDIES COLL PK MD 20742
Titolo Testata:
IEEE transactions on neural networks
fascicolo: 3, volume: 5, anno: 1994,
pagine: 502 - 504
SICI:
1045-9227(1994)5:3<502:EONCOC>2.0.ZU;2-5
Fonte:
ISI
Lingua:
ENG
Tipo documento:
Letter
Natura:
Periodico
Settore Disciplinare:
CompuMath Citation Index
Science Citation Index Expanded
Science Citation Index Expanded
Science Citation Index Expanded
Science Citation Index Expanded
Citazioni:
9
Recensione:
Indirizzi per estratti:
Citazione:
G.G. Sutton e J.A. Reggia, "EFFECTS OF NORMALIZATION CONSTRAINTS ON COMPETITIVE LEARNING", IEEE transactions on neural networks, 5(3), 1994, pp. 502-504

Abstract

Implementations of competitive learning often use input and weight vectors ''normalized'' based on the sum of weight vector components. While it is realized that some distortion of results can occur with this procedure, it is generally not appreciated how dramatic the distortioncan be, and that it compromises the dot product as a similarity measure. We show here that in some cases an input vector identical to an existing output node weight vector can be classified as belonging to a different output node. This contradicts the generally-accepted concept of weight vectors developing as prototypes during competitive learning. Ways to minimize this problem are also given.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 31/03/20 alle ore 05:04:45