Detail publikačního výsledku

Self-Organizing Sparse Distributed Memory as a Predictive Memory

GREBENÍČEK, F.

Originální název

Self-Organizing Sparse Distributed Memory as a Predictive Memory

Anglický název

Self-Organizing Sparse Distributed Memory as a Predictive Memory

Druh

Stať ve sborníku mimo WoS a Scopus

Originální 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.

Anglický 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

Klíčová slova v angličtině

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

Autoři

GREBENÍČEK, F.

Vydáno

01.01.1999

Nakladatel

unknown

Místo

Zlín

ISBN

80-214-1424-3

Kniha

Nostradamus '99

Strany od

17

Strany do

22

Strany počet

6

URL

http://ft3.zlin.vutbr.cz/nostra/PRESENT/PRESENT.HTM

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"
}