Neural Comp. Sign up for ETOCS
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
QUICK SEARCH:   [advanced]


     

This Article
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via HighWire
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Stone, J. V.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Stone, J. V.

Neural Computation, Vol 8, 1463-1492, Copyright © 1996 by The MIT Press

ARTICLES

Learning perceptually salient visual parameters using spatiotemporal smoothness constraints

JV Stone
School of Cognitive and Computing Sciences, University of Sussex, UK.

A model is presented for unsupervised learning of low level vision tasks, such as the extraction of surface depth. A key assumption is that perceptually salient visual parameters (e.g., surface depth) vary smoothly over time. This assumption is used to derive a learning rule that maximizes the long-term variance of each unit's outputs, whilst simultaneously minimizing its short-term variance. The length of the half-life associated with each of these variances is not critical to the success of the algorithm. The learning rule involves a linear combination of anti-Hebbian and Hebbian weight changes, over short and long time scales, respectively. This maximizes the information throughput with respect to low-frequency parameters implicit in the input sequence. The model is used to learn stereo disparity from temporal sequences of random-dot and gray-level stereograms containing synthetically generated subpixel disparities. The presence of temporal discontinuities in disparity does not prevent learning or generalization to previously unseen image sequences. The implications of this class of unsupervised methods for learning in perceptual systems are discussed.


This article has been cited by other articles:


Home page
 Neural Comput.Home page
R. Turner and M. Sahani
A maximum-likelihood interpretation for slow feature analysis.
Neural Comput., April 1, 2007; 19(4): 1022 - 1038.
[Abstract] [Full Text] [PDF]

Home page
 Neural Comput.Home page
G. de A. Barreto, A. F. R. Araujo, and S. C. Kremer
A Taxonomy for Spatiotemporal Connectionist Networks Revisited: The Unsupervised Case
Neural Comput., June 1, 2003; 15(6): 1255 - 1320.
[Abstract] [Full Text] [PDF]

Home page
 Neural Comput.Home page
J. Hurri and A. Hyvarinen
Simple-Cell-Like Receptive Fields Maximize Temporal Coherence in Natural Video
Neural Comput., March 1, 2003; 15(3): 663 - 691.
[Abstract] [Full Text] [PDF]

Home page
 Neural Comput.Home page
L. Wiskott and T. J. Sejnowski
Slow Feature Analysis: Unsupervised Learning of Invariances
Neural Comput., April 1, 2002; 14(4): 715 - 770.
[Abstract] [Full Text] [PDF]

Home page
 Neural Comput.Home page
J. V. Stone
Blind Source Separation Using Temporal Predictability
Neural Comput., July 1, 2001; 13(7): 1559 - 1574.
[Abstract] [Full Text]


HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
J COGNITIVE NEUROSCIENCE NEURAL COMPUTATION MIT PRESS JOURNALS
Copyright © 1996 by The MIT Press.