Error Bounds for Functional Approximation and Estimation Using Mixtures of Experts

@article{Zeevi1998ErrorBF,
  title={Error Bounds for Functional Approximation and Estimation Using Mixtures of Experts},
  author={Assaf J. Zeevi and Ron Meir and Vitaly Maiorov},
  journal={IEEE Trans. Information Theory},
  year={1998},
  volume={44},
  pages={1010-1025}
}
We examine some mathematical aspects of learning unknown mappings with the Mixture of Experts Model MEM Speci cally we observe that the MEM is at least as powerful as a class of neural networks in a sense that will be made precise Upper bounds on the approximation error are established for a wide class of target functions The general theorem states that inf kf fnkp c n r d holds uniformly for f W r p L a Sobolev class over d where fn belongs to an n dimensional manifold of normalized ridge… CONTINUE READING

From This Paper

Topics from this paper.
21 Citations
20 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 20 references

Estimation, Inference and Speci cation Analysis, Cambridge university

  • H. White
  • 1994
Highly Influential
16 Excerpts

Neural Networks for Optimal Approximation of Smooth and Analytic Functions

  • H. Mhashar
  • Neural Computation,
  • 1995
Highly Influential
9 Excerpts

Estimation of Dependences Based on Empirical Data, Springer-Verlag

  • V. Vapnik
  • 1982
Highly Influential
7 Excerpts

Consequences and Detection of Misspeci ed Nonlinear Regression Mod- els

  • H. White
  • J. Amer. Statis. Assoc.,
  • 1981
Highly Influential
3 Excerpts

A New Look at the Statistical Model Identi cation

  • H. Akakike
  • IEEE Trans. AC,
  • 1974
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…