Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
CLASSIFICATION OF TRAJECTORIES - EXTRACTING INVARIANTS WITH A NEURAL-NETWORK
Autore:
KINDER M; BRAUER W;
Indirizzi:
TECH UNIV MUNICH,FAK INFORMAT,ARCISSTR 21 W-8000 MUNICH 2 GERMANY
Titolo Testata:
Neural networks
fascicolo: 7, volume: 6, anno: 1993,
pagine: 1011 - 1017
SICI:
0893-6080(1993)6:7<1011:COT-EI>2.0.ZU;2-3
Fonte:
ISI
Lingua:
ENG
Keywords:
INVARIANT REPRESENTATION; TASK-DEPENDENT SIMILARITY MEASURE; TOPOLOGICAL; DISTRIBUTED ENCODING; WICKEL FEATURES; TUPLE CODING; DELTA RULE; PERCEPTRON;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
CompuMath Citation Index
CompuMath Citation Index
Science Citation Index Expanded
Science Citation Index Expanded
Science Citation Index Expanded
Citazioni:
9
Recensione:
Indirizzi per estratti:
Citazione:
M. Kinder e W. Brauer, "CLASSIFICATION OF TRAJECTORIES - EXTRACTING INVARIANTS WITH A NEURAL-NETWORK", Neural networks, 6(7), 1993, pp. 1011-1017

Abstract

A neural classifier of planar trajectories is presented. There already exist a large variety of classifiers that are specialized in particular invariants contained in a trajectory classification task such as position-invariance, rotation-invariance, and size-invariance. That is,there exist classifiers specialized in recognizing trajectories, eg.,independently of their position. The neural classifier presented in this paper is not restricted to certain invariants in a task: The neural network itself extracts the invariants contained in a classificationtask by assessing only the trajectories. The trajectories need to be given as a set of points. No additional information must be available for training, which saves the designer from determining the needed invariants by himself Besides its applicability to real-world problems, such a more general classifier is also cognitively plausible: In assessing trajectories for classification, human beings are able to find class specific features no matter what kinds of invariants they are confronted with, Invariants are easily handled by ignoring unspecific features.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/11/20 alle ore 07:25:20