1. Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML), pp. 807–814 (2010)
2. Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, Vol. 15, pp. 315–323. PMLR (2011)
3. Arora, R., Basu, A., Mianjy, P., Mukherjee, P.: Understanding deep neural networks with rectified linear units. In: International Conference on Learning Representations (ICLR) (2018)
4. Hwang, W.-L., Tung, S.-S.: Analysis of function approximation and stability of general dnns in directed acyclic graphs using un-rectifying analysis. Electronics 12(18), 3858 (2023)
5. Heinecke, A., Ho, J., Hwang, W.-L.: Refinement and universal approximation via sparsely connected Relu convolution nets. IEEE Signal Process. Lett. 27, 1175–1179 (2020)