The Vanishing Empirical Variance in Randomly Initialized Deep ReLU Networks
Authors:
- 30 September 2025
- book chapter
- Published by Springer Nature
- p. 362-379
Abstract
No abstract availableKeywords
This publication has 7 references indexed in Scilit:
- Deep Residual Learning for Image Recognition2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Some Useful Moment Results in Sampling ProblemsThe American Statistician, 2014
- Efficient BackProp1998
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Neural Networks for Pattern Recognition1995
- Learning long-term dependencies with gradient descent is difficultIEEE Transactions on Neural Networks, 1994