메뉴 건너뛰기




Volumn 19, Issue 2, 2008, Pages 284-298

Best approximation of Gaussian neural networks with nodes uniformly spaced

Author keywords

Best approximation; Existence; Functions band limited in frequency; Gaussian radial basis functions (RBFs); Sampling theory; Truncation; Uniqueness

Indexed keywords

GAUSSIAN DISTRIBUTION; HILBERT SPACES; SAMPLING;

EID: 40549110625     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2007.905851     Document Type: Article
Times cited : (14)

References (70)
  • 2
    • 34250594054 scopus 로고
    • Functions entières et intégrales de fourier multiples
    • M. Plancherel and G. Pólya, "Functions entières et intégrales de fourier multiples," Comment. Math. Hel., vol. 10, pp. 110-163, 1937-1938.
    • (1937) Comment. Math. Hel , vol.10 , pp. 110-163
    • Plancherel, M.1    Pólya, G.2
  • 3
    • 0031996528 scopus 로고    scopus 로고
    • Communication in the presence of noise
    • Feb
    • C. E. Shannon, "Communication in the presence of noise," Proc. IEEE vol. 86, no. 2, pp. 447-457, Feb. 1998.
    • (1998) Proc. IEEE , vol.86 , Issue.2 , pp. 447-457
    • Shannon, C.E.1
  • 4
    • 0036288736 scopus 로고    scopus 로고
    • On the representation of band limited functions using finitely many bits
    • Jun
    • H. N. Mhaskar, "On the representation of band limited functions using finitely many bits," J. Complexity, vol. 18, no. 2, pp. 449-478, Jun. 2002.
    • (2002) J. Complexity , vol.18 , Issue.2 , pp. 449-478
    • Mhaskar, H.N.1
  • 5
    • 0034171723 scopus 로고    scopus 로고
    • Sampling - 50 years after Shannon
    • Apr
    • M. Unser, "Sampling - 50 years after Shannon," Proc. IEEE, vol. 88, no. 4, pp. 569-587, Apr. 2000.
    • (2000) Proc. IEEE , vol.88 , Issue.4 , pp. 569-587
    • Unser, M.1
  • 7
    • 0000106040 scopus 로고
    • Universal approximation using radial-basis-function networks
    • J. Park and I. W. Sandberg, "Universal approximation using radial-basis-function networks," Neural Comput., vol. 3, no. 2, pp. 246-257, 1991.
    • (1991) Neural Comput , vol.3 , Issue.2 , pp. 246-257
    • Park, J.1    Sandberg, I.W.2
  • 9
    • 33847387324 scopus 로고    scopus 로고
    • Connections between signal processing and complex analysis
    • J. Bruna, X. Massaneda, and J. Ortega-Cerdà, "Connections between signal processing and complex analysis," Contrib. Sci., vol. 2, no. 3, pp. 345-357, 2003.
    • (2003) Contrib. Sci , vol.2 , Issue.3 , pp. 345-357
    • Bruna, J.1    Massaneda, X.2    Ortega-Cerdà, J.3
  • 10
    • 40549123322 scopus 로고    scopus 로고
    • F. Girosi and G. Anzellotti, Convergence rates of approximation by translates, Massachusetts Inst. Technol., Artif. Intell. Lab., Cntr. Biol. Inf. Process., Whitaker College, Cambridge, MA, Tech. Rep. A.I. Memo. C.B.I.P. Paper No. 73, 1995.
    • F. Girosi and G. Anzellotti, "Convergence rates of approximation by translates," Massachusetts Inst. Technol., Artif. Intell. Lab., Cntr. Biol. Inf. Process., Whitaker College, Cambridge, MA, Tech. Rep. A.I. Memo. C.B.I.P. Paper No. 73, 1995.
  • 11
    • 5844296842 scopus 로고
    • On applications of approximation theory to identification, control and classification,
    • Ph.D. dissertation, Dept. Electr. Comp. Eng, Inf. Syst. Eng. Area, Univ. Texas, Arlington, TX
    • A. T. Dingankar, "On applications of approximation theory to identification, control and classification," Ph.D. dissertation, Dept. Electr. Comp. Eng., Inf. Syst. Eng. Area, Univ. Texas, Arlington, TX, 1995.
    • (1995)
    • Dingankar, A.T.1
  • 12
    • 0027599793 scopus 로고
    • Universal approximation bounds for superpositions of a sigmoidal function
    • May
    • A. R. Barron, "Universal approximation bounds for superpositions of a sigmoidal function," IEEE Trans. Inf. Theory, vol. 39, no. 3, pp. 930-945, May 1993.
    • (1993) IEEE Trans. Inf. Theory , vol.39 , Issue.3 , pp. 930-945
    • Barron, A.R.1
  • 13
    • 0039564241 scopus 로고
    • Optimal complexity recovery of band- and energy-limited signals
    • Sep
    • M. A. Kowalski, "Optimal complexity recovery of band- and energy-limited signals," J. Complexity, vol. 2, no. 3, pp. 239-254, Sep. 1986.
    • (1986) J. Complexity , vol.2 , Issue.3 , pp. 239-254
    • Kowalski, M.A.1
  • 14
    • 38249026178 scopus 로고
    • Optimal complexity recovery of band-and energy-limited signals ii
    • Mar
    • M. A. Kowalski and F. Stenger, "Optimal complexity recovery of band-and energy-limited signals ii," J. Complexity, vol. 5, no. 1, pp. 45-59, Mar. 1989.
    • (1989) J. Complexity , vol.5 , Issue.1 , pp. 45-59
    • Kowalski, M.A.1    Stenger, F.2
  • 15
    • 0026954302 scopus 로고
    • Gaussian networks for direct adaptive control
    • Nov
    • R. M. Sanner and J. E. Slotine, "Gaussian networks for direct adaptive control," IEEE Trans. Neural Netw., vol. 3, no. 6, pp. 837-863, Nov. 1992.
    • (1992) IEEE Trans. Neural Netw , vol.3 , Issue.6 , pp. 837-863
    • Sanner, R.M.1    Slotine, J.E.2
  • 17
    • 34250122797 scopus 로고
    • Interpolation of scattered data: Distance matrices and conditionally positive definite functions
    • C. A. Micchelli, "Interpolation of scattered data: Distance matrices and conditionally positive definite functions," Constructive Approx. vol. 2, pp. 11-12, 1986.
    • (1986) Constructive Approx , vol.2 , pp. 11-12
    • Micchelli, C.A.1
  • 18
    • 0024991997 scopus 로고
    • Networks and the best approximation property
    • F. Girosi and T. Poggio, "Networks and the best approximation property," Biol. Cybern., vol. 63, pp. 169-176, 1990.
    • (1990) Biol. Cybern , vol.63 , pp. 169-176
    • Girosi, F.1    Poggio, T.2
  • 19
    • 0012019432 scopus 로고
    • Massachusetts Inst. Technol, Artif. Intell. Lab, Cntr. Biol. Inf. Process, Whitaker College, Cambridge, MA, Tech. Rep
    • F. Girosi and T. Poggio, "Networks and the best approximation property," Massachusetts Inst. Technol., Artif. Intell. Lab., Cntr. Biol. Inf. Process., Whitaker College, Cambridge, MA, Tech. Rep., 1989.
    • (1989) Networks and the best approximation property
    • Girosi, F.1    Poggio, T.2
  • 21
    • 33847351007 scopus 로고    scopus 로고
    • The discrete characterization of Paley-Wiener space with several variables
    • G. Chen and G. Fang, "The discrete characterization of Paley-Wiener space with several variables," Prog. Natural Sci., vol. 13, pp. 300-303, 2003.
    • (2003) Prog. Natural Sci , vol.13 , pp. 300-303
    • Chen, G.1    Fang, G.2
  • 22
    • 0030140667 scopus 로고    scopus 로고
    • Whittaker-Kotelnikov-Shannnon sampling theorem and aliasing error
    • G. Fang, "Whittaker-Kotelnikov-Shannnon sampling theorem and aliasing error," J. Approx. Theory, vol. 85, pp. 115-131, 1996.
    • (1996) J. Approx. Theory , vol.85 , pp. 115-131
    • Fang, G.1
  • 23
    • 84968515233 scopus 로고
    • Five short stories about the cardinal series
    • J. R. Higgins, "Five short stories about the cardinal series," Bull Amer. Math. Soc., vol. 12, pp. 45-89, 1985.
    • (1985) Bull Amer. Math. Soc , vol.12 , pp. 45-89
    • Higgins, J.R.1
  • 24
    • 38249006054 scopus 로고
    • Irregular sampling of bandlimited LP-functions
    • G. Hinsen, "Irregular sampling of bandlimited LP-functions," J. Approx. Theory, vol. 72, pp. 346-364, 1993.
    • (1993) J. Approx. Theory , vol.72 , pp. 346-364
    • Hinsen, G.1
  • 25
  • 26
    • 84966200203 scopus 로고
    • Practical and mathematical aspects of the problem of reconstructing objects from radiographs
    • K. T. Smith, D. C. Solomon, and S. L. Wagner, "Practical and mathematical aspects of the problem of reconstructing objects from radiographs," Bull. Amer. Math. Soc., vol. 83, pp. 1227-1270, 1977.
    • (1977) Bull. Amer. Math. Soc , vol.83 , pp. 1227-1270
    • Smith, K.T.1    Solomon, D.C.2    Wagner, S.L.3
  • 28
    • 0036587729 scopus 로고    scopus 로고
    • Fourier frames
    • J. Ortega-Cerdá and K. Seip, "Fourier frames," Ann. Math, vol. 155, no. 3, pp. 789-806, 2002.
    • (2002) Ann. Math , vol.155 , Issue.3 , pp. 789-806
    • Ortega-Cerdá, J.1    Seip, K.2
  • 29
    • 0242357464 scopus 로고    scopus 로고
    • Learning and Generalization With Applications to Neural Networks
    • London, U.K, Springer-Verlag
    • M. Vidyasagar, Learning and Generalization With Applications to Neural Networks, ser. Communications and Control Engineering. London, U.K.: Springer-Verlag, 2003.
    • (2003) ser. Communications and Control Engineering
    • Vidyasagar, M.1
  • 30
    • 0027698750 scopus 로고
    • A perceptron network for functional identification and control of nonlinear systems
    • Nov
    • N. Sadegh, "A perceptron network for functional identification and control of nonlinear systems," IEEE Trans. Neural Netw., vol. 4, no. 6, pp. 982-988, Nov. 1993.
    • (1993) IEEE Trans. Neural Netw , vol.4 , Issue.6 , pp. 982-988
    • Sadegh, N.1
  • 31
    • 0001558197 scopus 로고
    • Positive de nite functions and generalizations, an historical survey
    • J. Stewart, "Positive de nite functions and generalizations, an historical survey," Rocky Mountain J. Math, vol. 6, pp. 409-434, 1976.
    • (1976) Rocky Mountain J. Math , vol.6 , pp. 409-434
    • Stewart, J.1
  • 32
    • 0344993943 scopus 로고    scopus 로고
    • Approximation by neural networks is not continuous
    • P. C. Kainen, V. Kurková, and A. Vogt, "Approximation by neural networks is not continuous," Neurocomputing, vol. 29, pp. 47-56, 1999.
    • (1999) Neurocomputing , vol.29 , pp. 47-56
    • Kainen, P.C.1    Kurková, V.2    Vogt, A.3
  • 33
    • 0004485678 scopus 로고
    • On the algebraic structure of feedforward network weight spaces
    • R. Hecht-Nielsen, "On the algebraic structure of feedforward network weight spaces," Adv. Neural Comput., pp. 129-135, 1990.
    • (1990) Adv. Neural Comput , pp. 129-135
    • Hecht-Nielsen, R.1
  • 34
    • 0026897370 scopus 로고
    • Uniqueness of the weights for minimal feedforward nets with a given input-output map
    • H. Sussmann, "Uniqueness of the weights for minimal feedforward nets with a given input-output map," Neural Netw., vol. 5, pp. 589-594, 1992.
    • (1992) Neural Netw , vol.5 , pp. 589-594
    • Sussmann, H.1
  • 35
    • 21844505259 scopus 로고
    • Neural networks for localized approximation
    • C. Chui, X. Li, and H. Mhaskar, "Neural networks for localized approximation," Math. Comput., vol. 63, pp. 607-623, 1994.
    • (1994) Math. Comput , vol.63 , pp. 607-623
    • Chui, C.1    Li, X.2    Mhaskar, H.3
  • 36
    • 24544481301 scopus 로고
    • Uniqueness of functional representations by Gaussian basis function networks
    • London, U.K
    • V. Kurkova and R. Neruda, "Uniqueness of functional representations by Gaussian basis function networks," in Proc. Int. Conf. Artif. Neural Netw., London, U.K., 1994, pp. 471-474.
    • (1994) Proc. Int. Conf. Artif. Neural Netw , pp. 471-474
    • Kurkova, V.1    Neruda, R.2
  • 37
    • 0024880831 scopus 로고
    • Multilayer feedforward networks are universal approximators
    • K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Netw., vol. 2, pp. 359-366, 1989.
    • (1989) Neural Netw , vol.2 , pp. 359-366
    • Hornik, K.1    Stinchcombe, M.2    White, H.3
  • 38
    • 0025636775 scopus 로고
    • The Stone-Weierstrass theorem and its application to neural networks
    • Dec
    • N. E. Cotter, "The Stone-Weierstrass theorem and its application to neural networks," IEEE Trans. Neural Netw., vol. 1, no. 4, pp. 290-295, Dec. 1990.
    • (1990) IEEE Trans. Neural Netw , vol.1 , Issue.4 , pp. 290-295
    • Cotter, N.E.1
  • 40
    • 0024866495 scopus 로고
    • On the approximate realization of continuous mappings by neural networks
    • K.-I. Funahashi, "On the approximate realization of continuous mappings by neural networks," Neural Netw., vol. 2, pp. 183-192, 1989.
    • (1989) Neural Netw , vol.2 , pp. 183-192
    • Funahashi, K.-I.1
  • 41
    • 0026627415 scopus 로고
    • Kolmogorov's theorem and multilayer neural networks
    • V. Kurkova, "Kolmogorov's theorem and multilayer neural networks," Neural Netw., vol. 5, pp. 501-506, 1992.
    • (1992) Neural Netw , vol.5 , pp. 501-506
    • Kurkova, V.1
  • 42
    • 0028262894 scopus 로고
    • Computational aspects of Kolmogorov's superposition theorem
    • H. Katsuura and D. Sprecher, "Computational aspects of Kolmogorov's superposition theorem," Neural Netw., vol. 7, pp. 455-461, 1994.
    • (1994) Neural Netw , vol.7 , pp. 455-461
    • Katsuura, H.1    Sprecher, D.2
  • 43
    • 0027842059 scopus 로고
    • A universal mapping for Kolmogorov's superposition theorem
    • D. Sprecher, "A universal mapping for Kolmogorov's superposition theorem," Neural Netw., vol. 6, pp. 1089-1094, 1993.
    • (1993) Neural Netw , vol.6 , pp. 1089-1094
    • Sprecher, D.1
  • 44
    • 0025751820 scopus 로고
    • Approximation capabilities of multilayer feedforward networks
    • K. Hornik, "Approximation capabilities of multilayer feedforward networks," Neural Netw., vol. 4, pp. 251-257, 1991.
    • (1991) Neural Netw , vol.4 , pp. 251-257
    • Hornik, K.1
  • 45
    • 0028387201 scopus 로고
    • Good weights and hyperbolic kernels for neural networks, projection pursuit, and pattern classification: Fourier strategies for extracting information from high-dimensional data
    • Mar
    • L. Jones, "Good weights and hyperbolic kernels for neural networks, projection pursuit, and pattern classification: Fourier strategies for extracting information from high-dimensional data," IEEE Trans. Inf. Theory, vol. 40, no. 2, pp. 439-454, Mar. 1994.
    • (1994) IEEE Trans. Inf. Theory , vol.40 , Issue.2 , pp. 439-454
    • Jones, L.1
  • 46
    • 0027189305 scopus 로고
    • On the complexity of approximating mappings using feed-forward networks
    • P. Koiran, "On the complexity of approximating mappings using feed-forward networks," Neural Netw., vol. 6, pp. 649-653, 1993.
    • (1993) Neural Netw , vol.6 , pp. 649-653
    • Koiran, P.1
  • 47
    • 0027262895 scopus 로고
    • Multilayer feedforward networks with a nonpolynomial activation can approximate any function
    • M. Leshno, V. Y. Lin, A. Pinkus, and S. Schocken, "Multilayer feedforward networks with a nonpolynomial activation can approximate any function," Neural Netw., vol. 6, pp. 861-867, 1993.
    • (1993) Neural Netw , vol.6 , pp. 861-867
    • Leshno, M.1    Lin, V.Y.2    Pinkus, A.3    Schocken, S.4
  • 48
    • 0006863682 scopus 로고
    • Approximation properties of a multilayered feedforward artificial neural network
    • Dordrecht, The Netherlands: Springer-Verlag
    • H. Mhaskar, "Approximation properties of a multilayered feedforward artificial neural network," in Advances in Computational Mathematics Dordrecht, The Netherlands: Springer-Verlag, 1993, vol. 1, pp. 61-80.
    • (1993) Advances in Computational Mathematics , vol.1 , pp. 61-80
    • Mhaskar, H.1
  • 49
    • 0024861871 scopus 로고
    • Approximation by superpositions of a sigmoidal function
    • G. Cybenko, "Approximation by superpositions of a sigmoidal function," Math. Control Signals Syst., vol. 2, no. 4, pp. 303-314, 1989.
    • (1989) Math. Control Signals Syst , vol.2 , Issue.4 , pp. 303-314
    • Cybenko, G.1
  • 51
    • 0034266877 scopus 로고    scopus 로고
    • Best approximation by heaviside perceptron networks
    • P. C. Kainen, V. Kurková, and A. Vogt, "Best approximation by heaviside perceptron networks," Neural Netw., vol. 13, pp. 695-697, 2000.
    • (2000) Neural Netw , vol.13 , pp. 695-697
    • Kainen, P.C.1    Kurková, V.2    Vogt, A.3
  • 53
    • 0028497289 scopus 로고
    • The best approximation to C2 functions and its error bounds using regular-center Gaussian networks
    • Sep
    • B. Liu and J. Si, "The best approximation to C2 functions and its error bounds using regular-center Gaussian networks," IEEE Trans. Neural Netw., vol. 5, no. 5, pp. 845-847, Sep. 1994.
    • (1994) IEEE Trans. Neural Netw , vol.5 , Issue.5 , pp. 845-847
    • Liu, B.1    Si, J.2
  • 54
    • 0027735783 scopus 로고
    • The best approximation properties and error bounds of Gaussian networks
    • San Antonio, TX, Dec
    • B. Liu and J. Si, "The best approximation properties and error bounds of Gaussian networks," in Proc. IEEE 32nd Conf. Decision Control, San Antonio, TX, Dec. 1993, pp. 2798-2803.
    • (1993) Proc. IEEE 32nd Conf. Decision Control , pp. 2798-2803
    • Liu, B.1    Si, J.2
  • 55
    • 0028748447 scopus 로고
    • The best approximation to C2 functions and its error bounds using regular-center Gaussian networks
    • B. Liu and J. Si, "The best approximation to C2 functions and its error bounds using regular-center Gaussian networks," in Proc. Int. Conf. Neural Netw. Control, 1994, pp. 2400-2406.
    • (1994) Proc. Int. Conf. Neural Netw. Control , pp. 2400-2406
    • Liu, B.1    Si, J.2
  • 56
    • 0000672424 scopus 로고
    • Fast learning in networks of locally-tuned processing units
    • J. Moody and C. Darken, "Fast learning in networks of locally-tuned processing units," Neural Comput., vol. 1, no. 2, pp. 281-294, 1989.
    • (1989) Neural Comput , vol.1 , Issue.2 , pp. 281-294
    • Moody, J.1    Darken, C.2
  • 57
    • 0025490985 scopus 로고
    • Networks for approximation and learning
    • Sep
    • T. Poggio and F. Girosi, "Networks for approximation and learning," Proc. IEEE, vol. 78, no. 9, pp. 1481-1497, Sep. 1990.
    • (1990) Proc. IEEE , vol.78 , Issue.9 , pp. 1481-1497
    • Poggio, T.1    Girosi, F.2
  • 58
    • 0025037991 scopus 로고
    • A network that learns to recognize 3D objects
    • T. Poggio and S. Edelman, "A network that learns to recognize 3D objects," Nature, vol. 343, pp. 263-266, 1990.
    • (1990) Nature , vol.343 , pp. 263-266
    • Poggio, T.1    Edelman, S.2
  • 59
    • 0038669853 scopus 로고
    • Approximation by uniformly spaced Gaussian functions
    • E. Cheney, Ed. New York: Academic
    • R. Klopfenstein and R. Sverdlove, "Approximation by uniformly spaced Gaussian functions," in Approximation Theory IV, E. Cheney, Ed. New York: Academic, 1983, pp. 575-580.
    • (1983) Approximation Theory IV , pp. 575-580
    • Klopfenstein, R.1    Sverdlove, R.2
  • 62
    • 0003771069 scopus 로고    scopus 로고
    • Centre de recherches mathématiques, Université de Montréal, Montreal, QC, Canada
    • P. Koosis, "Leçons sur le théorème de beurling et malliavin," Centre de recherches mathématiques, Université de Montréal, Montreal, QC, Canada, 1996.
    • (1996) Leçons sur le théorème de beurling et malliavin
    • Koosis, P.1
  • 64
    • 0344835879 scopus 로고    scopus 로고
    • Hierarchical RBF networks and local parameters estimate
    • N. A. Borghese and S. Ferrari, "Hierarchical RBF networks and local parameters estimate," Neurocomputing, pp. 259-283, 1998.
    • (1998) Neurocomputing , pp. 259-283
    • Borghese, N.A.1    Ferrari, S.2
  • 65
    • 1242331283 scopus 로고    scopus 로고
    • Multiscale approximation with hierarchical radial basis functions networks
    • Jan
    • S. Ferrari, M. Maggioni, and N. A. Borghese, "Multiscale approximation with hierarchical radial basis functions networks," IEEE Trans. Neural Netw., vol. 15, no. 1, pp. 178-188, Jan. 2004.
    • (2004) IEEE Trans. Neural Netw , vol.15 , Issue.1 , pp. 178-188
    • Ferrari, S.1    Maggioni, M.2    Borghese, N.A.3
  • 67
    • 40549094930 scopus 로고
    • Madrid, Spain: Universidad Nacional de Educación a Distancia UNED
    • E. L. Escardó, Análisis Matemático II. Madrid, Spain: Universidad Nacional de Educación a Distancia (UNED), 1991.
    • (1991) Análisis Matemático II
    • Escardó, E.L.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.