Radon transform and differentiable approximation by neural networks

@article{Ito1993RadonTA,
  title={Radon transform and differentiable approximation by neural networks},
  author={Yoshifusa Ito},
  journal={Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan)},
  year={1993},
  volume={3},
  pages={2288-2291 vol.3}
}
We treat the problem of simultaneously approximating C/sup m/-functions in several variables and their derivatives by superpositions of a fixed activation function in one variable. The domain of approximation can be either compact subsets or the whole Euclidean space. If the domain is compact, the activation function does not need to be scalable. Even if the domain is the whole space, the activation function can be used without scaling under a certain condition. The approximation can be… CONTINUE READING