Learning spatially coherent properties of the visual world in connectionist networks

Suzanna Becker; Geoffrey E. Hinton

doi:10.1117/12.48380

1 October 1991 Learning spatially coherent properties of the visual world in connectionist networks

Suzanna Becker, Geoffrey E. Hinton

Proceedings Volume 1569, Stochastic and Neural Methods in Signal Processing, Image Processing, and Computer Vision; (1991) https://doi.org/10.1117/12.48380
Event: San Diego, '91, 1991, San Diego, CA, United States

Abstract

In the unsupervised learning paradigm, a network of neuron-like units is presented with an ensemble of input patterns from a structured environment, such as the visual world, and learns to represent the regularities in that input. The major goal in developing unsupervised learning algorithms is to find objective functions that characterize the quality of the network's representation without explicitly specifying the desired outputs of any of the units. The sort of objective functions considered cause a unit to become tuned to spatially coherent features of visual images (such as texture, depth, shading, and surface orientation), by learning to predict the outputs of other units which have spatially adjacent receptive fields. Simulations show that using an information-theoretic algorithm called IMAX, a network can be trained to represent depth by observing random dot stereograms of surfaces with continuously varying disparities. Once a layer of depth-tuned units has developed, subsequent layers are trained to perform surface interpolation of curved surfaces, by learning to predict the depth of one image region based on depth measurements in surrounding regions. An extension of the basic model allows a population of competing neurons to learn a distributed code for disparity, which naturally gives rise to a representation of discontinuities.

Citation Download Citation

Suzanna Becker and Geoffrey E. Hinton "Learning spatially coherent properties of the visual world in connectionist networks", Proc. SPIE 1569, Stochastic and Neural Methods in Signal Processing, Image Processing, and Computer Vision, (1 October 1991); https://doi.org/10.1117/12.48380

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Stochastic processes

Visualization

Image processing

Sensors

Machine learning

Computer vision technology

Machine vision

Show All Keywords

Keywords/Phrases

Search In:

Publication Years