1. Understanding the difficulty of training deep feedforward neural networks;glorot;Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics,2010
2. Error bounds for approximations with deep ReLU networks
3. Automatic differentiation in pytorch;paszke;Proceedings of 31st Conference on Neural Information Processing Systems,2017
4. Decoupled weight decay regularization;loshchilov;arXiv 1711 05101,2017
5. Why deep neural networks for function approximation?;liang;Proceedings of 5th International Conference on Learning Representations ICLR 2017,2019