|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| H. Shvayster, "Learnable and Nonlearnable Visual Concepts," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 5, pp. 459-466, May, 1990. | |||
| BibTex | x | ||
| @article{ 10.1109/34.55105, author = {H. Shvayster}, title = {Learnable and Nonlearnable Visual Concepts}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {12}, number = {5}, issn = {0162-8828}, year = {1990}, pages = {459-466}, doi = {http://doi.ieeecomputersociety.org/10.1109/34.55105}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - JOUR JO - IEEE Transactions on Pattern Analysis and Machine Intelligence TI - Learnable and Nonlearnable Visual Concepts IS - 5 SN - 0162-8828 SP459 EP466 EPD - 459-466 A1 - H. Shvayster, PY - 1990 KW - learnable visual concepts; learnability; nonlearnable visual concepts; Valiant's theory; learning systems; pattern recognition VL - 12 JA - IEEE Transactions on Pattern Analysis and Machine Intelligence ER - | |||
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).
[1] A. Blumer, A. Ehrenfeucht, D. Haussler, and M. K. Warmuth, "Learnability and the Vapnik-Chervonenkis dimension,"J. Ass. Comput. Mach., vol. 36, no. 4, pp. 929-965, Oct. 1989.
[2] B. Bollobas,Extremal Graph Theory. New York: Academic, 1978.
[3] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis. New York: Wiley, 1973.
[4] D. Haussler, M. Kearns, N. Littlestone, and M. Warmuth, "Equivalence of models for polynomial learnability," inProc. 1st Workshop Computational Learning Theory. Morgan Kaufmann, 1988, pp. 42- 55.
[5] M. Kearns, M. Li, L. Pitt, and L. G. Valiant, "On the learnability of boolean formulae," inProc. 19th Annu. ACM Symp. Theory of Computing, May 1987, pp. 285-295.
[6] D. Marr,Vision, San Francisco, CA: Freeman, 1982.
[7] M. Minsky and S. Papert,Perceptrons: An Introduction to Computational Geometry. Cambridge, MA: MIT Press, 1969.
[8] J. Piper and D. Rutovitz, "An investigation of object-oriented programming as the basis for an image processing and analysis system," inProc. 9th Int. Conf. Patt. Recog., 1988, pp. 1015-1019.
[9] L. Pitt, and L. G. Valiant, "Computational limitations on learning from examples,"J. ACM, vol. 33, no. 4, pp. 965-984, 1988.
[10] R. L. Rivest, "Learning decision lists,"Mach. Learning, vol. 2, pp. 229-246, 1987.
[11] A. Rosenfeld and A. Kak,Digital Picture Processing, New York: Academic, 1976.
[12] D.E. Rumelhart and D. McClelland, eds.,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vols. 1-2, MIT Press, Cambridge, Mass., 1986.
[13] H. Shvaytser, "A necessary condition for learning from positive examples,"Machine Learning, vol. 5, no. 1, pp. 101-103, 1990.
[14] J. K. Tsotsos, "Analyzing vision at the complexity level,"Behavioral Brain Sci., vol. 12, no. 3, 1990.
[15] L. G. Valiant, "A theory of the learnable,"Comm. ACM, vol. 27, pp. 1134-1142, Nov. 1984.
[16] L. G. Valiant, "Learning disjunctions of conjunctions," inProc. 9th IJCAI, Aug. 1985, pp. 550-556.