Neural networks with local receptive fields and superlinear VC dimension

Neural Computation

Volumn 14, Issue 4, 2002, Pages 919-956

  Schmitt, Michael ^a  

^a RUHR UNIVERSITY BOCHUM   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL MODEL; ELECTROPHYSIOLOGY; NERVE CELL; PHYSIOLOGY; STATISTICAL MODEL;

ALGORITHMS; ELECTROPHYSIOLOGY; LINEAR MODELS; MODELS, NEUROLOGICAL; NEURAL NETWORKS (COMPUTER); NEURONS;

EID: 0036551211     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976602317319018     Document Type: Article

References (58)

1. Anthony, M. (1995). Classification by polynomial surfaces. Discrete Applied Mathematics, 61, 91-103.
2. Anthony, M., & Bartlett, P. L. (1999). Neural network learning: Theoretical foundations. Cambridge: Cambridge University Press.
3. Anthony, M., & Holden, S. B. (1994). Quantifying generalization in linearly weighted neural networks. Complex Systems, 8, 91-114.
4. Assouad, P. (1983). Densité et dimension. Annales de l'Institut Fourier, 33(3), 233-282.
5. Atick, J. J., & Redlich, A. N. (1993). Convergent algorithm for sensory receptive field development. Neural Computation, 5, 45-60.
6. Bartlett, P. L., Maiorov, V., & Meir, R. (1998). Almost linear VC dimension bounds for piecewise polynomial networks. Neural Computation, 10, 2159-2173.
7. Bartlett, P. L., & Williamson, R. C. (1996). The VC dimension and pseudodimension of two-layer neural networks with discrete inputs. Neural Computation, 8, 625-628.
8. Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford: Clarendon Press.
9. Blumer, A., Ehrenfeucht, A., Haussler, D., & Warmuth, M. K. (1989). Learnability and the Vapnik-Chervonenkis dimension. Journal of the Association for Computing Machinery, 36, 929-965.
10. Broomhead, D. S., & Lowe, D. (1988). Multivariable functional interpolation and adaptive networks. Complex Systems, 2, 321-355.
11. Cover, T. M. (1965). Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Transactions on Electronic Computers, 14, 326-334.
12. k do not cut all subsets of k + 2 points. Advances in Mathematics, 31, 306-308.
13. Enroth-Cugell, C., & Robson, J. G. (1966). The contrast sensitivity of retinal ganglion cells of the cat. Journal of Physiology, 187, 517-552.
14. Erlich, Y., Chazan, D., Petrack, S., & Levy, A. (1997). Lower bound on VC-dimension by local shattering. Neural Computation, 9, 771-776.
15. Glezer, V. D. (1995). Vision and mind: Modeling mental functions. Mahwah, NJ: Erlbaum.
16. Hartman, E. J., Keeler, J. D., & Kowalski, J. M. (1990). Layered neural networks with gaussian hidden units as universal approximations. Neural Computation, 2, 210-215.
17. Haussler, D. (1992). Decision theoretic generalizations of the PAC model for neural net and other learning applications.-Information and Computation, 100, 78-150.
18. Hawken, M. J., & Parker, A. J. (1987). Spatial properties of neurons in the monkey striate cortex. Proceedings of the Royal Society of London, Series B, 231, 251-288.
19. Holden, S. B., & Rayner, P. J. W. (1995). Generalization and PAC learning: Some new results for the class of generalized single-layer networks. IEEE Transactions on Neural Networks, 6, 368-380.
20. Howlett, R. J., & Jain, L. C. (Eds.). (2001a). Radial basis function networks 1: Recent developments in theory and applications. Berlin: Springer-Verlag.
21. Howlett, R. J., & Jain, L. C. (Eds.). (2001b). Radial basis function networks 2: New advances in design. Berlin: Springer-Verlag.
22. Joshi, A., & Lee, C.-H. (1993). Backpropagation learns Marr's operator. Biological Cybernetics, 70, 65-73.
23. Karpinski, M., & Macintyre, A. (1997). Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks. Journal of Computer and System Sciences, 54, 169-176.
24. Koiran, P., & Sontag, E. D. (1997). Neural networks with quadratic VC dimension. Journal of Computer and System Sciences, 54, 190-198.
25. Kuffler, S. W. (1953). Discharge patterns and functional organization of mammalian retina. Journal of Neurophysiology, 16, 37-68.
26. Lee, W. S., Bartlett, P. L., & Williamson, R. C. (1995). Lower bounds on the VC dimension of smoothly parameterized function classes. Neural Computation, 7, 1040-1053.
27. Lee, W. S., Bartlett, P. L., & Williamson, R. C. (1997). Correction to "Lower bounds on VC-dimension of smoothly parameterized function classes." Neural Computation, 9, 765-769.
28. Linsker, R. (1986). From basic network principles to neural architecture: Emergence of spatial-opponent cells. Proceedings of the National Academy of Sciences USA, 83, 7508-7512.
29. Linsker, R. (1988). Self-organization in a perceptual network. Computer, 21(3), 105-117.
30. Liu, S.-C, & Boahen, K. (1996). Adaptive retina with center-surround receptive field. In D. S. Touretzky, M. C. Mozer, & M. E. Hasselmo (Eds.), Advances in neural information processing systems, 8 (pp. 678-684). Cambridge, MA: MIT Press.
31. Maass, W. (1993). Bounds on the computational power and learning complexity of analog neural nets. In Proceedings of the 25th Annual ACM Symposium on Theory of Computing (pp. 335-344). New York: ACM Press.
32. Maass, W. (1994). Neural nets with super-linear VC-dimension. Neural Computation, 6, 877-884.
33. Maass, W., & Schmitt, M. (1999). On the complexity of learning for spiking neurons with temporal coding. Information and Computation, 153, 26-46.
34. Marr, D. (1982). Vision: A computational investigation into the human representation and processing of visual information. New York: Freeman.
35. Marr, D., & Hildreth, E. (1980). Theory of edge detection. Proceedings of the Royal Society of London. Series B, 207, 187-217.
36. Mead, C. (1989). Analog VLSI and neural systems. Reading, MA: Addison-Wesley.
37. Mead, C. A., & Mahowald, M. A. (1988). A silicon model of early visual processing. Neural Networks, 1, 91-97.
38. Mhaskar, H. N. (1996). Neural networks for optimal approximation of smooth and analytic functions. Neural Computation, 8, 164-177.
39. Moody, J., & Darken, C. J. (1989). Fast learning in networks of locally-tuned processing units. Neural Computation, 1, 281-294.
40. Natschläger, T., & Schmitt, M. (1996). Exact VC-dimension of Boolean monomials. Information Processing Letters, 59, 19-20. (Erratum Information Processing Letters, 60, 107, 1996.)
41. Nicholls, J. G., Martin, A. R., & Wallace, B. G. (1992). From neuron to brain: A cellular and molecular approach to the function of the nervous system (3rd ed.). Sunderland, MA: Sinauer Associates.
42. Nilsson, N. J. (1990). The mathematical foundations of learning machines. San Mateo, CA: Morgan Kaufmann.
43. Park, J., & Sandberg, I. W. (1991). Universal approximation using radial-basis-function networks. Neural Computation, 3, 246-257.
44. Park, J., & Sandberg, I. W. (1993). Approximation and radial-basis-function networks. Neural Computation, 5, 305-316.
45. Poggio, T., & Girosi, F. (1990). Networks for approximation and learning. Proceedings of the IEEE, 78, 1481-1497.
46. Powell, M. J. D. (1992). The theory of radial basis function approximation in 1990. In W. Light (Ed.), Advances in numerical analysis II: Wavelets, subdivision algorithms, and radial basis functions (pp. 105-210). Oxford: Clarendon Press.
47. Ripley, B. D. (1996). Pattern recognition and neural networks. Cambridge: Cambridge University Press.
48. Rodieck, R. W. (1965). Quantitative analysis of cat retinal ganglion cell response to visual stimuli. Vision Research, 5, 583-601.
49. Sakurai, A. (1993). Tighter bounds of the VC-dimension of three layer networks. In Proceedings of the World Congress on Neural Networks (Vol. 3, pp. 540-543). Hillsdale, NJ: Erlbaum.
50. Schläfli, L. (1901). Theorie der vielfachen Kontinuität. Zürich: Zürcher & Furrer.
51. Schmidhuber, J., Eldracher, M., & Foltin, B. (1996). Semilinear predictability minimization produces well-known feature detectors. Neural Computation, 8, 773-786.
52. Schmitt, M. (2000). On the complexity of computing and learning with multiplicative neural networks. Neural Computation, in press.
53. Shawe-Taylor, J. (1995). Sample sizes for threshold networks with equivalences. Information and Computation, 118, 65-72.
54. Tessier-Lavigne, M. (1991). Phototransduction and information processing in the retina. In E. R. Kandel, J. H. Schwartz, & T. M. Jessell (Eds.), Principles of neural science (3rd ed., pp. 400-418). Englewood Cliffs, NJ: Prentice Hall.
55. Ward, V., & Syrzycki, M. (1995). VLSI implementation of receptive fields with current-mode signal processing for smart vision sensors. Analog Integrated Circuits and Signal Processing, 7, 167-179.
56. Wenocur, R. S., & Dudley, R. M. (1981). Some special Vapnik-Chervonenkis classes. Discrete Mathematics, 33, 313-318.
57. Yasui, S., Furukawa, T., Yamada, M., & Saito, T. (1996). Plasticity of center-surround opponent receptive fields in real and artificial neural systems of vision. In D. S. Touretzky, M. C. Mozer, & M. E. Hasselmo (Eds.), Advances in neural information processing systems, 8 (pp. 159-165). Cambridge, MA: MIT Press.
58. Yee, P., & Haykin, S. (2001). Regularized radial-basis function networks: Theory and applications. New York: Wiley.