Liu, Y., J. Ge, C. Li, and J. Gui. “Delving into Variance Transmission and Normalization: Shift of Average Gradient Makes the Network Collapse”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 3, May 2021, pp. 2216-24, doi:10.1609/aaai.v35i3.16320.