Detail výsledku

Self-Organizing Sparse Distributed Memory as a Predictive Memory

GREBENÍČEK, F. Self-Organizing Sparse Distributed Memory as a Predictive Memory. Nostradamus '99. Zlín: unknown, 1999. p. 17-22. ISBN: 80-214-1424-3.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Grebeníček František, Ing., FEKT (FEKT)
Abstrakt

The paper discuses an extension of Kanerva's Sparse Distributed Memory (SDM) and introduces possible application in prediction. A self-organizing SDM equivalent to a three-layered neural network is used to learn the desired transfer function mapping a history of velocity vectors to predicted velocity vector. The net was tested in simple mouse-tracking experiment, but can be used in more handy problems, for example in motion capturing systems.

Klíčová slova

Neural Net, Self-Organizing Map, Soft Competitive Learning Rule, Sparse Distributed Memory, Prediction

URL
Rok
1999
Strany
17–22
Sborník
Nostradamus '99
ISBN
80-214-1424-3
Vydavatel
unknown
Místo
Zlín
BibTeX 
@inproceedings{BUT192155,
  author="František {Grebeníček}",
  title="Self-Organizing Sparse Distributed Memory as a Predictive Memory",
  booktitle="Nostradamus '99",
  year="1999",
  pages="17--22",
  publisher="unknown",
  address="Zlín",
  isbn="80-214-1424-3",
  url="http://ft3.zlin.vutbr.cz/nostra/PRESENT/PRESENT.HTM"
}
Projekty
Výzkum a aplikace heterogenních modelů, GAČR, Standardní projekty, GA102/98/0552, zahájení: 1998-01-01, ukončení: 2000-12-31, ukončen
Výzkumné skupiny
Výzkumná skupina inteligentních systémů (VZ INTSYS)
Pracoviště
Fakulta informačních technologií (FIT)
Nahoru