SHU Short Course on Principles of AI for Control and Optimization

Schedule, Information, and Material

SHU Short Course on Principles of AI for Control and Optimization

This extended short course introduces and discusses basic concepts of machine learning and how they relate to principles and applications of control and optimization theory.

The first 4 weeks will be held given by Timm Faulwasser and team and focus on optimization aspects of the training of neural networks.

The second part is provided by Enrique Zuazua and directed towards control of dynamical systems and how this aligns with the theory of supervised learning.

The last part by Jan Heiland considers applications of neural networks for the formulation of control tasks.

The Time Schedule

Date Lecturer Lecture
September 07: 15:00–16:40 TF/JH 01 Introduction
September 09: 15:00–16:40 TF 02 Questions and Challenges
September 14: 15:00–16:40 TF 03 Optimization :loop: VooV: 684 7858 1174
September 16: 15:00–16:40 TF 04 Challenges and Tasks in Optimization :loop: VooV: 714 153 178
September 21: 15:00–16:40 TF Note: cancelled
September 23: 15:00–16:40 TF 05 Gaussian Processes :loop: VooV: 714 153 178
September 28: 15:00–16:40 TF :loop: VooV: 684 7858 1174
September 30: 15:00–16:40 TF :loop: VooV: 714 153 178
October 05: 15:00–16:40 EZ Note: cancelled
October 07: 15:00–16:40 EZ Note: shifted to Saturday
October 09: 15:00–16:40 EZ Note: Saturday :loop: VooV: 770 795 439
October 12: 15:00–16:40 EZ :loop: VooV: 684 7858 1174
October 14: 15:00–16:40 EZ :loop: VooV: 714 153 178
October 19: 15:00–16:40 EZ :loop: VooV: 684 7858 1174
October 21: 15:00–16:40 EZ :loop: VooV: 714 153 178
October 26: 15:00–16:40 EZ :loop: VooV: 684 7858 1174
October 28: 15:00–16:40 EZ :loop: VooV: 714 153 178
November 02: 15:00–16:40 JH 17 Physics Informed Neural Network :loop: BBB
November 04: 15:00–16:40 JH 18 Convolutional Neural Networks :loop: Zoom: 69133989530
November 09: 15:00–16:40 JH 19 Wrapup and Studying in Germany :loop: Zoom: 69615001183
November 11: 15:00–16:40 JH 20 Introduction to PyTorch :loop: Zoom: 69133989530

All times are Beijing time.

Links to the Course Materials

All material can be found here. With file names corresponding to the lectures. Please also see the details of every lecture.

Details of the Lecture

01 Introduction

01-01 Introduction to Machine Learning and Optimization

Resources

01-02 PDEs, Dynamical Systems, CNN

Resources

02 Challenges-Tasks on Basic Notions of Machine Learning

Resources

03 Optimization

04 Challenges and Tasks in Optimization

05 Gaussian Processes

17 Physics Informed Neural Networks – PINN

  1. Wrapup on how Neural Networks can assist with (or even replace) the costly simulation of PDEs.

  2. Little preview on Data encoding by NN.

  3. What constitutes a Neural Network and how to make it physics informed.

  4. Training an backward mode to compute the gradients for the optimization.

18 Convolutional Neural Networks

19 PINN ctd. and Studying abroad (maybe a Master in Magdeburg)

A more general look on PINN and Examples

Doing a Master or PhD in Germany

For all questions around studying abroad, contact the SHU international office.

20 Introduction to PyTorch

Little Chinese Dictionary

Hello 你好
Matrix 矩阵
Vector 向量
Eigenvalue 特征值
Projection 投影
Subspace 子空间
Interpolation 插值
Model 模型
System 系统
Transfer function 传递函数
Stable 稳定
Truncation 截断