This course discusses various aspects of an important class of scientific machine learning, namely scientific deep learning. To that end, the course will cover the following topics (with certain depths including proofs of relevant theorems): 1) statistical machine learning framework with deep learning, 2) universal approximation theorem for ReLU network 3) Back-propagation for gradient computation. If time permits, we will cover the gradient vanishing problem in deep learning and ResNet as an approach to overcome these problems
This course discusses various aspects of an important class of scientific machine learning, namely scientific deep learning. To that end, the course will cover the following topics (with certain depths including proofs of relevant theorems): 1) statistical machine learning framework with deep learning, 2) universal approximation theorem for ReLU network 3) Back-propagation for gradient computation. If time permits, we will cover the gradient vanishing problem in deep learning and ResNet as an approach to overcome these problems
-
-
Guest Lecture:
Tan Bui-Than - The Oden Institute for Computational Engineering and Sciences, University of Texas at Austin
Guest Lecture:
Tan Bui-Than - The Oden Institute for Computational Engineering and Sciences, University of Texas at Austin