Kernel Limit for a Class of Recurrent Neural Networks Trained on Ergodic Data Sequences
循环神经网络在ergodic数据序列上的核极限
机构 * Mathematical Institute, University of Oxford(牛津大学数学研究所) ; Department of Mathematics & Statistics, Boston University(波士顿大学数学与统计学系)
AI总结 该研究发展了RNN在ergodic数据序列上的核极限理论,通过固定点分析和微分方程处理,解决了RNN在大规模数据和隐藏单元下的收敛问题。
Comments Revision in response to reviewers' comments. The mean-field random function has been replaced by a mean-field term. Some typos fixed. Minor title change