Learnable and nonlearnable visual concepts
Shvaytser, H.
David Sarnoff Res. Center, Princeton, NJ;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: May 1990
Volume: 12,
Issue: 5
On page(s): 459-466
ISSN: 0162-8828
References Cited: 16
CODEN: ITPIDJ
INSPEC Accession Number: 3700280
Digital Object Identifier: 10.1109/34.55105
Current Version Published: 2002-08-06
Abstract
Valiant's theory of the learnable is applied to visual concepts in
digital pictures. Several visual concepts that are easily perceived by
humans are shown to be learnable from positive examples. These concepts
include a certain type of inaccurate copies of line drawings,
identifying a subset of objects at specific locations, and pictures of
lines in a fixed slope. Several characterizations of visual concepts by
templates are shown to be nonlearnable (in the sense of Valiant) from
positive-only examples. The importance of representations is
demonstrated by showing that even though one can easily learn to
identify pictures with at least one of two objects, identifying the
objects is sometimes much harder (computationally infeasible)
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
