Recurrent autoassociative networks and holistic computations

Author

Stoianov, Ivelin

Author_Institution

Dept. Alfa-Inf., Groningen Univ., Netherlands

Volume

5

fYear

2000

fDate

2000

Firstpage

605

Abstract

Presents an experimental study of holistic computations over distributed representations (DRs) of sequences developed by recurrent autoassociative networks (RANs). Three groups of holistic operators are studied: extracting symbols at fixed positions, extracting symbols at variable positions, and reversing strings. Success with those operators and the very good generalization achieved pave the way for holistic linguistic transformations. Also, it brings a better understanding of the structure of the DRs developed by the RANs

Keywords

associative processing; generalisation (artificial intelligence); mathematical operators; recurrent neural nets; sequences; symbol manipulation; distributed representations; fixed positions; generalization; holistic computations; holistic linguistic transformations; holistic operators; recurrent autoassociative networks; sequences; string reversal; symbol extraction; variable positions; Art; Computer networks; Data mining; Decoding; Distributed computing; Kalman filters; Neural networks; Radio access networks; Roads; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.861535

Filename

861535