G. Yang. (2019)cite arxiv:1902.04760Comment: tldr: A theoretical tool for understanding the behavior of large width randomly initialized neural networks for almost all deep learning architectures.
A. Matthews, M. Rowland, J. Hron, R. Turner, and Z. Ghahramani. (2018)cite arxiv:1804.11271Comment: This work substantially extends the work of Matthews et al. (2018) published at the International Conference on Learning Representations (ICLR) 2018.