Lectures

I would like to thank Prof. Alexander Schwing, Prof. Aigou Han, Prof. Farzad Kamalabadi, and Prof. Corey Synder for their support and lecture documents which I’ve based much of my own work on.

Also, quick hint, icons are links to slides and video contents! Also if the video link hasn’t appeared on the website, you can check the mediaspace channel directly!

# Title Date Slides(HTML) Slides(Code) Recording
0 Lecture 0 - PyTorch Intro, tensors, views, indexing Jan 21 Lecture 0 slides Lecture 0 code Lecture 0 recording
1 Lecture 1 - PyTorch storage, indexing, cpu/gpu data types, functions Jan 23 Lecture 1 slides Lecture 1 code Lecture 1 recording
2 Lecture 2 - Linear algebra I Jan 28 Lecture 2 slides Lecture 2 code Lecture 2 recording
3 Lecture 3 - Linear algebra II & Matrix algebra Jan 30 Lecture 3 slides Lecture 3 code Lecture 3 recording
4 Lecture 4 - Matrix calculus II and computation graphs Feb 04 Lecture 4 slides Lecture 4 code Lecture 4 recording
5 Lecture 5 - Gradient descent Feb 06 Lecture 5 slides Lecture 5 code Lecture 5 recording
6 Lecture 6 - Primal optimization Feb 11 Lecture 6 slides Lecture 6 code Lecture 6 recording
7 Lecture 7 - Linear regression I Feb 13 Lecture 7 slides Lecture 7 code Lecture 7 recording
8 Lecture 8 - Linear regression II Feb 18 Lecture 8 slides Lecture 8 code Lecture 8 recording
9 Lecture 9 - Logistic regression Feb 20 Lecture 9 slides Lecture 9 code Lecture 9 recording
10 Lecture 10 - Multi-class logistic regression Feb 25 Lecture 10 slides Lecture 10 code Lecture 10 recording
11 Lecture 11 - PyTorch optimizers, datasets, dataloaders I Feb 27 Lecture 11 slides Lecture 11 code Lecture 11 recording
12 Lecture 12 - PyTorch optimizers, datasets, dataloaders II Mar 04 Lecture 12 slides Lecture 12 code Lecture 12 recording
13 Lecture 13 - Review for MT1 Mar 06 Lecture 13 slides Lecture 13 code Lecture 13 recording
14 Lecture 14 - Deep Nets I - Simple, multi-layer networks Mar 25 Lecture 14 slides Lecture 14 code Lecture 14 recording
15 Lecture 15 - Deep Nets II - Convolutional networks Mar 27 Lecture 15 slides Lecture 15 code Lecture 15 recording
16 Lecture 16 - Deep Nets III - Recurrent networks Apr 01 Lecture 16 slides Lecture 16 code Lecture 16 recording
17 Lecture 17 - Principal component analysis Apr 03 Lecture 17 slides Lecture 17 code Lecture 17 recording
18 Lecture 18 - K-means clustering, gaussian mixture models Apr 08 Lecture 18 slides Lecture 18 code
19 Lecture 19 - Generative adversarial networks Apr 10 Lecture 19 slides Lecture 19 code Lecture 19 recording
20 Lecture 20 - Object detection, semantic segmentation Apr 15 Lecture 20 slides Lecture 20 code Lecture 20 recording
21 Lecture 21 - Words and attention Apr 17 Lecture 21 slides Lecture 21 code Lecture 21 recording
22 Lecture 22 - Transformers I Apr 22 Lecture 22 slides Lecture 22 code Lecture 22 recording
23 Lecture 23 - Transformers II Apr 24 Lecture 23 slides Lecture 23 code Lecture 23 recording
24 Lecture 24 - Midterm 2 review Apr 29 Lecture 24 slides Lecture 24 code Lecture 24 recording
25 Lecture 25 - Course recap and farewell May 06 Lecture 25 slides Lecture 25 code Lecture 25 recording

Site created by Nickvash Kani using the backend from the Mathematical Language Processing Group website.
Electrical and Computer Engineering Department at the University of Illinois at Urbana-Champaign