BIMSA >
Seminar on Control Theory and Nonlinear Filtering
Bidirectional Recurrent Neural Networks Are Universal Smoothers
Bidirectional Recurrent Neural Networks Are Universal Smoothers
Organizer
Speaker
Yangtianze Tao
Time
Tuesday, November 22, 2022 9:00 PM - 9:30 PM
Venue
Online
Abstract
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.