publication . Article . Other literature type . 2005

Learning viewpoint invariant object representations using a temporal coherence principle

Name: Learning viewpoint invariant object representations using a temporal coherence principle
Keywords: Biotechnology, General Computer Science

Julian Eggert; Peter König; Jörg Hipp; Wolfgang Einhäuser; Edgar Körner;

Open Access English

Published: 01 Jul 2005

Summary

Abstract

Invariant object recognition is arguably one of the major challenges for contemporary machine vision systems. In contrast, the mammalian visual system performs this task virtually effortlessly. How can we exploit our knowledge on the biological system to improve artificial systems? Our understanding of the mammalian early visual system has been augmented by the discovery that general coding principles could explain many aspects of neuronal response properties. How can such schemes be transferred to system level performance? In the present study we train cells on a particular variant of the general principle of temporal coherence, the “stability” objective. These...

doi: 10.3929/ethz-b-000032109 , 10.1007/s00422-005-0585-8

Subjects

free text keywords: Biotechnology, General Computer Science, Coherence (physics), Unsupervised learning, Complex system, Machine vision, Artificial intelligence, business.industry, business, Invariant (mathematics), Form perception, Coding (social sciences), Pattern recognition, Viewpoints, Computer science

Related Organizations