Liu Y, Ge J, Li C, Gui J. Delving into Variance Transmission and Normalization: Shift of Average Gradient Makes the Network Collapse. AAAI [Internet]. 2021May18 [cited 2024Apr.25];35(3):2216-24. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/16320