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: 2–4pm, Mon)

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

TA’s:
Hengkang Wang (email: wang9881 AT umn.edu, office Hours: 1–3pm, Thur)
Yash Travadi (email: trava029 AT umn.edu, office Hours: 12–2pm, Fri)

Lecture Schedule

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] (supplementary notes)
Sep 20 Basics of numerical optimization: optimality conditions [Slides]
Sep 27 Basics of numerical optimization: iterative methods [Slides]
Oct 04 Basics of numerical optimization: computing derivatives [Slides]
Oct 11 Training DNNs: basic methods and tricks [Slides]
Oct 18 MSI tutorial [Slides]
Course project [Slides]
Oct 25 Unsupervised representation learning: autoencoders and factorization [Slides]
Nov 01 From fully-connected to convolutional neural networks [Slides]
Nov 08 Applications of CNNs in computer Vision: detection and segmentation [Slides]
Nov 15 Sequence modeling: recurrent neural networks [Slides]
Nov 22 Transformers [Slides]
Nov 29 Project lightning talks (no lecture content)
Dec 06 Generative models: generative adversarial networks, variational autoencoder, normalization flow, Diffusion models [Slides]
Dec 13 Relationship Modeling: Graph Neural Networks [Slides]

Homework