Bidirectional Recurrent Neural Networks Are Universal Smoothers
组织者
演讲者
陶飏天择
时间
2022年11月22日 21:00 至 21:30
地点
Online
摘要
In the presentation, I will give the proof for the universal approximation theorem of the BRNN-based smoother, i.e., any filtering dynamics can be well-approximated by the forward recursions of BRNNs while the corresponding smoothing dynamics will also be well-approximated by the backward recursions of the BRNNs.