Over the last few years, deep neural networks (DNNs) have fundamentally transformed the way people think of machine learning and approach practical problems. Successes around DNNs have ranged from traditional AI fields such as computer vision, natural language processing, interactive games, to healthcare, physical sciences—touching each and every corner of theoretical and applied domains. On the other hand, DNNs still largely operate as black-boxes and we only have very limited understanding as for when and why they work. This course introduces basic ingredients of DNNs, samples important applications, and throws around open problems. Emphasis is put on thinking from first principles and basic building blocks, as the field is still evolving rapidly and there is nothing there that cannot be changed.

Full syllabus: Syllabus.pdf

Instructor: Professor Ju Sun Email: jusun AT umn.edu (Office Hours: 1–3pm, Mon)

When/Where: Wed 6:30–9:00pm @ KHKH 3-210

TA’s:
Tiancong Chen (email: chen6271 AT umn.edu, office Hours: 10am-12pm Tue)
Jiandong Chen (email: chen8111 AT umn.edu, office Hours: 12-2pm Wed)

Lecture Schedule

Disclaimer: The schedule is tentative and subject to change

Date Topics  
Sep 06 Deep learning: overview [slides]
Neural networks: old and new [slides]		  
Sep 13 Fundamental belief: universal approximation theorems [slides]
Review of high-dimensional calculus [slides] [notes]		  
Sep 20 Basics of numerical optimization: optimality conditions [slides]
Basics of numerical optimization: iterative methods [slides]		  
Sep 27 Basics of numerical optimization: computing derivatives [slides]  
Oct 04 Introduction to Google Colab and PyTorch [slides] [Colab file]  
Oct 11 Training DNNs: basic methods and tricks [slides]  
Oct 18 Training DNNs: basic methods and tricks (continued)
Course project [slides]		  
Oct 25 From fully-connected to convolutional neural networks [slides]  
Nov 01 Applications of CNNs in computer Vision: detection and segmentation [slides]  
Nov 08 Sequence modeling: recurrent neural networks [slides]  
Nov 15 Transformers, large language models, and foundation models [slides]  
Nov 22 Project lightning talks (no lecture content)  
Nov 29 Relationship modeling: graph neural networks [slides]  
Dec 06 Unsupervised and self-supervised representation [slides]  
Dec 13 Deep generative models [slides]  

Homework