Legends: |
Link to a Model |
Reference cited by multiple papers |

## References and models cited by this paper | ## References and models that cite this paper | |

Adams RA, Fournier JJF (2003) Sobolev spacesBarron AR (1992) Neural net approximation Proc 7th Yale Workshop on Adaptive and Learning Systems, Narenda K, ed. pp.69Barron AR (1993) Universal approximation bounds for superposition of a sigmoidal function IEEE Trans Inform Theory 39:930-945Cybenko G (1989) Approximation by super positions of a sigmoidal function Math Control, Signals And Systems 2:303-314 [Journal] Fine TL (1999) Feedforward neural networks methodologyHornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators Neural Networks 2:359-366Ito Y (1991) Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Networks 4:385-394Jones LK (1992) A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training Ann Stat 20:608-613Kainen PC, Kurkova V, Vogt A (1999) Approximation by neural networks is not continuous Neurocomputing 29:47-56Kainen PC, Kurkova V, Vogt A (2000) Geometry and topology of continuous best and near best approximations J Approx Theory 105:252-262Kainen PC, Kurkova V, Vogt A (2000) An integral formula for Heaviside neural networks Neural Network World 10:313-320Kainen PC, Kurkova V, Vogt A (2003) Best approximation by linear combinations of characteristic functions of half-spaces J Approx Theory 122:151-159Kainen PC, Kurkova V, Vogt A (2006) ntegral combinations of Heavisides Research report ICS 966. Available online at http:--www.cs.cas.cz-research-publications.shtmlKainen PC, Kurkova V, Vogt A (2007) A Sobolev-type upper bound for rates of approximation by linear combinations of plane waves J Approx Theory 147:1-10Kreinovich V, Kainen PC, Kurková (1997) Estimates of the Number of Hidden Units and Variation with Respect to Half-Spaces. Neural Netw 10:1061-1068 [PubMed]Kurková , Savický P, Hlavácková K (1998) Representations and rates of approximation of real-valued Boolean functions by neural networks. Neural Netw 11:651-659 [PubMed]Kurkova V (1997) Dimension-independent rates of approximation by neural networks Computer-intensive methods in control and signal processing: The curse of dimensionality, Warwick K:Karny M, ed. pp.261Kurkova V (2003) High-dimensional approximation and optimization by neural networks Advances in learning theory: Methods, models and applications, Suykens J:Horvath G:Basu S:Micchelli C:Vandewalle J, ed. pp.69Kurkova V (2005) Minimization of empirical error functional over perceptron networks Adaptive and natural computing algorithms, Ribeiro B:Albrecht RF:Dobnikar A:Pearson DW:Steele NC, ed. pp.46Leshno M, Lin VY, Pinkus A, Schocken S (1993) Multilayer feedforward networks with a non-polynomial activation can approximate any function Neural Netw 6:861-867Mhaskar HN, Micchelli CA (1992) Approximation by superposition of a sigmoidal function Adv Appl Math 13:350-373Pisier G (1981) Remarques sur un resultat non publie de B. Maurey Seminaired Analyse Fonctionnelle 1980 81Shlafli L (1950) Gesamelte mathematische abhandlungenSinger I (1970) Best approximation in normed linear spaces by elements of linear subspacesStrichartz RS (2003) A guide to distribution theory and Fourier transformsVapnik V (1995) The Nature of Statistical Learning TheoryWerbos PJ (1985) Backpropagation: Basics and new developments The handbook of brain theory and neural networks, Arbib M, ed. pp.134 |