Minmin Chen, Jeffrey Pennington, and Samuel Schoenholz. Dynamical isometry and a mean field theory of RNNs: Gating enables signal propagation in recurrent neural networks. In Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, ...
《Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks》L Xiao, Y Bahri, J Sohl-Dickstein, S S. Schoenholz, J Pennington [Google Brain] (2018) O网页链接 view:O网页链接 k...
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks 来自 arXiv.org 喜欢 0 阅读量: 163 作者:M Chen,J Pennington,Schoenholz, Samuel S 摘要: Recurrent neural networks have gained widespread use in modeling sequence data across various ...