Liu, Yuxiang, Jidong Ge, Chuanyi Li, and Jie Gui. 2021. “Delving into Variance Transmission and Normalization: Shift of Average Gradient Makes the Network Collapse”. Proceedings of the AAAI Conference on Artificial Intelligence 35 (3):2216-24. https://ojs.aaai.org/index.php/AAAI/article/view/16320.