Corpus ID: 203641849

On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps

@article{Guss2019OnUA,
  title={On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps},
  author={William H. Guss and R. Salakhutdinov},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.01545}
}
  • William H. Guss, R. Salakhutdinov
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • The study of universal approximation of arbitrary functions $f: \mathcal{X} \to \mathcal{Y}$ by neural networks has a rich and thorough history dating back to Kolmogorov (1957). In the case of learning finite dimensional maps, many authors have shown various forms of the universality of both fixed depth and fixed width neural networks. However, in many cases, these classical results fail to extend to the recent use of approximations of neural networks with infinitely many units for functional… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 21 REFERENCES
    The Expressive Power of Neural Networks: A View from the Width
    236
    Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems
    315
    Learning Infinite-Layer Networks: Beyond the Kernel Trick
    5
    Gaussian Processes For Machine Learning
    316
    Computation with Infinite Neural Networks
    145
    Approximation capabilities of multilayer feedforward networks
    3360
    Steps Toward Deep Kernel Methods from Infinite Neural Networks
    40