Publication Details

Constructing Hierarchical Neural Nets Using Sparse Distributed Memory

GREBENÍČEK, F. Constructing Hierarchical Neural Nets Using Sparse Distributed Memory. ASIS 2000 Proceedings of the Colloquium. Sv. Hostýn, Bystřice pod Hostýnem: 2000. p. 359-364. ISBN: 80-85988-51-8.
Type
conference paper
Language
English
Authors
Grebeníček František, Ing.
URL
Keywords

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

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.

Annotation

This paper discusses a possibility of the hierarchical neural nets construction using Kanerva's Sparse Distributed Memory (SDM). SDM is an associative neural memory and can be used in visual pattern recognition. The paper introduces a hierarchical net for digit recognition. Results of xperiment show notable properties of the net: insensivity to digit position and warping. Finally, a possible modification of Fukushima's Neocognitron is discussed.

Published
2000
Pages
359–364
Proceedings
ASIS 2000 Proceedings of the Colloquium
Conference
22nd International Colloquium ASIS 2000 Advanced Simulation of Systems, Sv. Hostýn, Bystřice pod Hostýnem, CZ
ISBN
80-85988-51-8
Place
Sv. Hostýn, Bystřice pod Hostýnem
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",
  address="Sv. Hostýn, Bystřice pod Hostýnem",
  isbn="80-85988-51-8",
  url="http://www.fit.vutbr.cz/~grebenic/Publikace/asis2000.ps.zip"
}
Back to top