Share Email Print

Proceedings Paper

Visual grammars and their neural networks
Author(s): Eric Mjolsness
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We exhibit a systematic way to derive neural nets for vision problems. It involves formulating a vision problem as Bayesian inference or decision on a comprehensive model of the visual domain given by a probabilistic grammar. A key feature of this grammar is the way in which it eliminates model information, such as object labels, as it produces an image; correspondence problems and other noise removal tasks result. The neural nets that arise most directly are generalized assignment networks. Also there are transformations which naturally yield improved algorithms such as correlation matching in scale space and the Frameville neural nets for high-level vision. Networks derived this way generally have objective functions with spurious local minima; such minima may commonly be avoided by dynamics that include deterministic annealing, for example recent improvements to Mean Field Theory dynamics. The grammatical method of neural net design allows domain knowledge to enter from all levels of the grammar, including `abstract' levels remote from the final image data, and may permit new kinds of learning as well.

Paper Details

Date Published: 1 July 1992
PDF: 23 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140075
Show Author Affiliations
Eric Mjolsness, Yale Univ. (United States)

Published in SPIE Proceedings Vol. 1710:
Science of Artificial Neural Networks
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top