The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.05 - May (1990 vol.12)
pp: 459-466
ABSTRACT
<p>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).</p>
INDEX TERMS
learnable visual concepts; learnability; nonlearnable visual concepts; Valiant's theory; learning systems; pattern recognition
CITATION
H. Shvayster, "Learnable and Nonlearnable Visual Concepts", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.12, no. 5, pp. 459-466, May 1990, doi:10.1109/34.55105
41 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool