Approximate geometry representations and sensory fusion

Csaba Szepesvári, András Lorincz

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

Keywords

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

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Approximate geometry representations and sensory fusion'. Together they form a unique fingerprint.

  • Cite this