Approximate geometry representations and sensory fusion

Csaba Szepesvári, A. Lőrincz

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Information from the external world goes through various transformations. The learning of the original neighbourhood relations of the world using only the transformed information is examined in detail. An approximate representation consists of a finite number of discretizing points and connections between neighbouring points. The goal here is to develop the theory of self-organizing approximate representations. Such a self-organizing system may be considered as a generalization of the Kohonen topographical map that we now equip with self-organizing neigbouring connections. For illustrative purposes an example is presented for sensory fusion: the geometry of the 3D world is learned using the outputs of two cameras.

Original languageEnglish
Pages (from-to)267-287
Number of pages21
JournalNeurocomputing
Volume12
Issue number2-3
DOIs
Publication statusPublished - Jul 31 1996

Fingerprint

Self organizing maps
Fusion reactions
Cameras
Learning
Geometry

Keywords

  • Geometry representation
  • Kohonen network
  • Self-organizing networks
  • Sensory fusion
  • Topographical mapping

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Cite this

Approximate geometry representations and sensory fusion. / Szepesvári, Csaba; Lőrincz, A.

In: Neurocomputing, Vol. 12, No. 2-3, 31.07.1996, p. 267-287.

Research output: Contribution to journalArticle

Szepesvári, Csaba ; Lőrincz, A. / Approximate geometry representations and sensory fusion. In: Neurocomputing. 1996 ; Vol. 12, No. 2-3. pp. 267-287.
@article{0fe7dc0e2b874eb7b4ce48365d61e802,
title = "Approximate geometry representations and sensory fusion",
abstract = "Information from the external world goes through various transformations. The learning of the original neighbourhood relations of the world using only the transformed information is examined in detail. An approximate representation consists of a finite number of discretizing points and connections between neighbouring points. The goal here is to develop the theory of self-organizing approximate representations. Such a self-organizing system may be considered as a generalization of the Kohonen topographical map that we now equip with self-organizing neigbouring connections. For illustrative purposes an example is presented for sensory fusion: the geometry of the 3D world is learned using the outputs of two cameras.",
keywords = "Geometry representation, Kohonen network, Self-organizing networks, Sensory fusion, Topographical mapping",
author = "Csaba Szepesv{\'a}ri and A. Lőrincz",
year = "1996",
month = "7",
day = "31",
doi = "10.1016/0925-2312(95)00116-6",
language = "English",
volume = "12",
pages = "267--287",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "2-3",

}

TY - JOUR

T1 - Approximate geometry representations and sensory fusion

AU - Szepesvári, Csaba

AU - Lőrincz, A.

PY - 1996/7/31

Y1 - 1996/7/31

N2 - Information from the external world goes through various transformations. The learning of the original neighbourhood relations of the world using only the transformed information is examined in detail. An approximate representation consists of a finite number of discretizing points and connections between neighbouring points. The goal here is to develop the theory of self-organizing approximate representations. Such a self-organizing system may be considered as a generalization of the Kohonen topographical map that we now equip with self-organizing neigbouring connections. For illustrative purposes an example is presented for sensory fusion: the geometry of the 3D world is learned using the outputs of two cameras.

AB - Information from the external world goes through various transformations. The learning of the original neighbourhood relations of the world using only the transformed information is examined in detail. An approximate representation consists of a finite number of discretizing points and connections between neighbouring points. The goal here is to develop the theory of self-organizing approximate representations. Such a self-organizing system may be considered as a generalization of the Kohonen topographical map that we now equip with self-organizing neigbouring connections. For illustrative purposes an example is presented for sensory fusion: the geometry of the 3D world is learned using the outputs of two cameras.

KW - Geometry representation

KW - Kohonen network

KW - Self-organizing networks

KW - Sensory fusion

KW - Topographical mapping

UR - http://www.scopus.com/inward/record.url?scp=0030608138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030608138&partnerID=8YFLogxK

U2 - 10.1016/0925-2312(95)00116-6

DO - 10.1016/0925-2312(95)00116-6

M3 - Article

AN - SCOPUS:0030608138

VL - 12

SP - 267

EP - 287

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 2-3

ER -