Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney
TL;DR研究透过向隐含状态注入噪音训练的递归神经网络，已证实该方法可提升其稳定性及鲁棒性。
Abstract
We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. Specifically, we consider RNNs that can be viewed as discretizations of stochastic differential