Visual recognition and inference using dynamic overcomplete sparse learning

We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and expectation-driven segmentation. Using properties of biological vision for guidance, we posit a stochastic generative worl...

Full description

Bibliographic Details

Published in:	Neural computation Vol. 19; no. 9; p. 2301
Main Authors:	Murray, Joseph F, Kreutz-Delgado, Kenneth
Format:	Journal Article
Language:	English
Published:	United States 01.09.2007
Subjects:	Algorithms Artificial Intelligence Humans Learning - physiology Models, Neurological Nonlinear Dynamics Pattern Recognition, Visual - physiology Photic Stimulation
ISSN:	0899-7667
Online Access:	Get more information
Tags:	Add Tag No Tags, Be the first to tag this record!