Publication detail

Constructing Hierarchical Neural Nets Using Sparse Distributed Memory

GREBENÍČEK, F.

Original Title

Constructing Hierarchical Neural Nets Using Sparse Distributed Memory

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

This paper discusses a possibility of the hierarchical neural netsconstruction using Kanerva's Sparse Distributed Memory (SDM). SDM is anassociative neural memory and can be used in visual patternrecognition. The paper introduces a hierarchical net for digitrecognition. Results of xperiment show notable properties of the net:insensivity to digit position and warping. Finally, a possiblemodification of Fukushima's Neocognitron is discussed.

Keywords

Neural nets, associative memory, Sparse Distributed Memory, pattern recognition

Authors

GREBENÍČEK, F.

Released

1. 1. 2000

Publisher

Marq software s.r.o.

Location

Sv. Hostýn, Bystřice pod Hostýnem

ISBN

80-85988-51-8

Book

ASIS 2000 Proceedings of the Colloquium

Pages from

359

Pages to

364

Pages count

6

URL

http://www.fit.vutbr.cz/~grebenic/Publikace/asis2000.ps.zip

BibTex

@inproceedings{BUT192151,
  author="František {Grebeníček}",
  title="Constructing Hierarchical Neural Nets Using Sparse Distributed Memory",
  booktitle="ASIS 2000 Proceedings of the Colloquium",
  year="2000",
  pages="359--364",
  publisher="Marq software s.r.o.",
  address="Sv. Hostýn, Bystřice pod Hostýnem",
  isbn="80-85988-51-8",
  url="http://www.fit.vutbr.cz/~grebenic/Publikace/asis2000.ps.zip"
}