Differences

This shows you the differences between two versions of the page.

--- seminars:stat:sep72023 [2023/09/04 13:38] – created qyu
+++ seminars:stat:sep72023 [2023/09/07 16:38] (current) – qyu
@@ Line 1: / Line 1: @@
+<WRAP centeralign>##Statistics Seminar##\\ Department of Mathematics and Statistics</WRAP>
+<WRAP 70% center>
+^  **DATE:**|Thursday, September 7, 2023 |
+^  **TIME:**|1:15pm -- 2:15pm |
+^  **LOCATION:**|WH 100E |
+^  **SPEAKER:**|Jia Zhao, Binghamton University |
+^  **TITLE:**|Discovery of Governing Equations with Recursive Deep Neural Networks  |
+</WRAP>
+\\
+<WRAP center box 80%>
+<WRAP centeralign>**Abstract**</WRAP>
+Model discovery based on existing data has been one of the major focuses
+of mathematical modelers for decades. Despite tremendous achievements of model
+identification from adequate data, how to unravel the models from limited data is
+less resolved. In this talk, I will focus on the model discovery problem when the
+data is not efficiently sampled. This is common due to limited experimental
+accessibility and labor/resource constraints. Specifically, we introduce a recursive
+deep neural network (RDNN) for data-driven model discovery. By embedding the known
+physics knowledge, this recursive approach can retrieve the governing equation in a
+simple and efficient manner, and it can significantly improve the approximation
+accuracy by increasing the recursive stages. In particular, our proposed approach
+shows superior power when the existing data are sampled with a large time lag, from
+which the traditional approach might not be able to recover the model well. Several
+widely used examples of dynamical systems are used to benchmark this newly proposed
+recursive approach. Numerical comparisons confirm the effectiveness of this
+recursive neural network for model discovery.
+</WRAP>