1. Barron A R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans Inform Theory, 1993, 39: 930–945
2. Cybenko G. Approximation by superpositions of a sigmoidal function. Math Control Signal Syst, 1989, 2: 303–314
3. Liang S, Srikant R. Why deep neural networks for function approximation? ArXiv:1610.04161, 2016
4. Lu Z, Pu H, Wang F, et al. The expressive power of neural networks: A view from the width. In: Advances in Neural Information Processing Systems, vol. 30. Long Beach: Neural Information Processing Systems Foundation, 2017, 6232–6240
5. Montanelli H, Du Q. Deep ReLU networks lessen the curse of dimensionality. ArXiv:1712.08688, 2017