Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Dynamics and context dependence of visual category learning

Dynamics and context dependence of visual category learning Spatial Vision , Vol. 13, No. 2,3, pp. 231– 240 (2000) Ó VSP 2000. Dynamics and context dependence of visual category learning INGO RENTSCHLER and MARTIN JÜTTNER Institute of Medical Psychology, University of Munich, Munich, Germany Received 23 August 1999; accepted 14 March 2000 Abstract —Visual category learning by humans is observed within a paradigm of supervised learning. Mental representations for recognition are reconstructed from the observed data structures by Ž tting to them predicted classiŽ cation data obtained from similarity-based models of recognition on the one hand and machine vision systems for image understanding on the other hand. These principles are illustrated with examples concerning the dynamics and the dependence on context of processes of category learning. Keywords : Visual recognition; category learning; classiŽ cation; recognition-by-parts;context. 1. FOCUSING IN BETWEEN IGNORANCE AND KNOWLEDGE The expert radiologist recognises the source of an image signal often immediately and without effort, while the novice sees nothing else than shades of gray. Equally extreme are positions in vision research with regard to the nature of recognition. Many assume that it is mediated by feature extraction through Ž xed and invariant neural mechanisms, i.e. nothing is learned. Others, who are concerned with http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Spatial Vision (continued as Seeing & Perceiving from 2010) Brill

Dynamics and context dependence of visual category learning

Loading next page...
 
/lp/brill/dynamics-and-context-dependence-of-visual-category-learning-LRnc0zbUzZ

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Brill
Copyright
© 2000 Koninklijke Brill NV, Leiden, The Netherlands
ISSN
0169-1015
eISSN
1568-5683
DOI
10.1163/156856800741234
Publisher site
See Article on Publisher Site

Abstract

Spatial Vision , Vol. 13, No. 2,3, pp. 231– 240 (2000) Ó VSP 2000. Dynamics and context dependence of visual category learning INGO RENTSCHLER and MARTIN JÜTTNER Institute of Medical Psychology, University of Munich, Munich, Germany Received 23 August 1999; accepted 14 March 2000 Abstract —Visual category learning by humans is observed within a paradigm of supervised learning. Mental representations for recognition are reconstructed from the observed data structures by Ž tting to them predicted classiŽ cation data obtained from similarity-based models of recognition on the one hand and machine vision systems for image understanding on the other hand. These principles are illustrated with examples concerning the dynamics and the dependence on context of processes of category learning. Keywords : Visual recognition; category learning; classiŽ cation; recognition-by-parts;context. 1. FOCUSING IN BETWEEN IGNORANCE AND KNOWLEDGE The expert radiologist recognises the source of an image signal often immediately and without effort, while the novice sees nothing else than shades of gray. Equally extreme are positions in vision research with regard to the nature of recognition. Many assume that it is mediated by feature extraction through Ž xed and invariant neural mechanisms, i.e. nothing is learned. Others, who are concerned with

Journal

Spatial Vision (continued as Seeing & Perceiving from 2010)Brill

Published: Jan 1, 2000

Keywords: VISUAL RECOGNITION; RECOGNITION-BY-PARTS; CLASSIFICATION; CONTEXT; CATEGORY LEARNING

There are no references for this article.