| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
On Learning to Recognize 3-D Objects from Examples
August 1993 (vol. 15 no. 8)
pp. 833-837
Previous results on nonlearnability of visual concepts relied on the assumption that such concepts are represented as sets of pixels. The author uses an approach developed by Haussler (1989) to show that under an alternative, feature-based representation, recognition is probably approximately correct (PAC) learnable from a feasible number of examples in a distribution-free manner.
[1] H. Shvaytser, "Learnable and nonlearnable visual concepts,"IEEE Trans. Patt. Anal. Machine Intell., vol. 12, pp. 459-466, 1990.
[2] D. Haussler, "Generalizing the PAC model for neural net and other learning applications," UCSC-CRL 89-30, Univ. of California, Santa Cruz, 1989.
[3] L. G. Valiant, "A theory of the learnable,"Comm. ACM, vol. 27, pp. 1134-1142, Nov. 1984.
[4] H. Shvaytser, "Toward a computational theory of model based vision and perception," inProc. 3rd Int. Conf. Comput. Vision(Tokyo), 1990.
[5] T. Poggio and S. Edelman, "A network that learns to recognize three-dimensional objects,"Nature, vol. 343, pp. 263-266, 1990.
[6] S. Edelman and D. Weinshall, "A self-organizing multiple-view representation of 3D objects,"Biol. Cybern., vol. 64, pp. 209-219, 1991.
[7] D. Marr,Vision. San Francisco, CA: W. H. Freeman, 1982.
[8] K.R. Boff, L. Kaufman, and J. P. Thomas, Eds.,Handbook of Perception and Human Performance. New York: Wiley, 1986.
[9] I. Biederman and G. Ju, "Surface versus edge-based determinants of visual recognition,"Cognitive Psych., vol. 20, pp. 38-64, 1988.
[10] W. E. L. Grimson,From Images to Surfaces, Cambridge, MA: MIT Press, 1981.
[11] S. Ullman and R. Basri, "Recognition hy linear combinations of models," A. I. Memo 1152, Artificial Intell. Lab., Mass. Inst. Technol., 1990;IEEE Trans. Patt. Anal. Machine Intell., vol. 13, pp. 992-1005, 1991.
[12] S. Edelman and T. Poggio, "Bringing the Grandmother back into the picture: a memory-based view of object recognition," A. I. Memo 1181, Artificial Intell. Lab., Mass. Inst. of Technol., 1990;Int. J. Patt. Recog. Artif. Intell., vol. 6, pp. 37-61, 1992.
[13] S. Geman and C. -R. Hwang, "Nonparametric maximum likelihood estimation by the method of sieves,"Ann. Stat., vol. 10, pp. 400-414, 1982.
[14] D. Pollard,Convergence of Stochastic Processes. New York: Springer, 1984.
[15] P. C. Dodwell, "The Lie transformation group model of visual perception,"Perception Psychophys., vol. 34, pp 1-16, 1983.
[16] T. Tsao and L. Kanal, "A Lie group approach to visual perception," TR 1851. Univ. of Maryland, College Park, 1987.
[17] S. Ullman,The Interpretation of Visual Motion. Cambridge, MA: MIT Press, 1979.
[18] D. P. Huttenlocher and S. Ullman, "Object recognition using alignment," inProc. 1st Int. Conf. Comput. Vision(London), June 1987, pp. 102-111.
[19] D. G. Lowe, "Three-dimensional object recognition from single two-dimensional images,"Artificial Intell., vol. 31, 1987.
[20] B. Russell,Analysis of Mind. London: Allen and Unwin, 1921.
[21] T. Poggio and F. Girosi, "Regularization algorithms for learning that are equivalent to multilayer networks,"Sci., vol. 247, pp. 978-982, 1990.
[22] F. Girosi and T. Poggio, "Networks and best approximation property," AI Memo 1164, MIT, Oct. 1989.
[23] C. J. Stone, "Optimal global rates of convergence for nonparametric regression,"Ann. Stat., vol. 10, pp. 1040-1053, 1982.
[24] S. Ullman, "Computational studies in the interpretation of structure and motion: Summary and extension." inHuman and Machine Vision(J. Beck, B. Hope, and A. Rosenfeld, Eds.). New York: Academic, 1983.
[25] 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.
[26] S. Edelman, "Features of recognition." CS-TR 10, Weizmann Inst. of Sci., 1991.
Index Terms:
learning by examples; image recognition; nonlearnability; visual concepts; Haussler; feature-based representation; image recognition; knowledge representation; learning by example
Citation:
S. Edelman, "On Learning to Recognize 3-D Objects from Examples," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 8, pp. 833-837, Aug. 1993, doi:10.1109/34.236244
