Applied Machine Learning (CS 441) – Spring 2023
Instructor: Derek Hoiem
Lectures: Tues/Thurs 9:30-10:45, 1002 ECE Building
Syllabus
Lecture Recordings Transcriptions
Lecture Review Questions and Answers
CampusWire Discussion (code: 6897)
Canvas Submission
Textbook: Applied Machine Learning by David Forsyth
Assignments
HW 1 – Intro to Classification and Regression (Feb 6)HW 2 – Trees, Ensembles, and MLPs (Feb 27)HW 3 – Application Domains and Foundation Models (Mar 27)HW 4 – Pattern Discovery (Apr 17)Final Project (May 3) |
|
|
|
|
|
|
Class Schedule (subject to change)
|
Week |
Date |
Topic |
Link |
Reading/Notes |
|
1 |
Jan 17 (Tues) |
Introduction |
||
|
|
|
Supervised Learning Fundamentals |
|
|
|
1 |
Jan 19 (Thurs) |
KNN, key concepts in ML |
AML Ch 1 |
|
|
2 |
Jan 24 (Tues) |
Probability and Naïve Bayes |
AML Ch 1 |
|
|
2 |
Jan 26 (Thurs) |
Linear Least Squares and Logistic Regression |
AML 10.1-10.2, 11 |
|
|
3 |
Jan 31 (Tues) |
Decision Trees |
AML Ch 2 |
|
|
3 |
Feb 2 (Thurs) |
Consolidation and Review |
|
|
|
|
Feb 6 (Mon) |
HW 1 (Classification & Regression) due |
|
|
|
4 |
Feb 7 (Tues) |
Ensembles and Random Forests |
AML Ch 2, Ch 12 |
|
|
4 |
Feb 9 (Thurs) |
SVMs and SGD |
AML Ch 2 |
|
|
5 |
Feb 14 (Tues) |
MLPs and Backprop |
AML Ch 16 |
|
|
5 |
Feb 16 (Thurs) |
Deep Learning |
AML Ch 16; ResNet (He et al. 2016) |
|
|
6 |
Feb 21 (Tues) |
Consolidation and Review |
|
|
|
|
|
Vision, Language, and Applications |
|
|
|
6 |
Feb 23 (Thurs) |
CNNs in Computer Vision |
AML Ch 17-18, PyTorch Tutorial from CS444 |
|
|
7 |
Feb 27 (Mon) |
HW 2 (Trees & MLPs) due |
|
|
|
7 |
Feb 28 (Tues) |
Words and Attention |
Sub-word Tokenization (Sennrich et al. 2016) Word2Vec (Mikolov et al. 2013) Attention is all you need (Vaswani et al. 2017) |
|
|
7 |
Mar 2 (Thurs) |
Transformers in Language and Vision |
BERT (Devlin et al. 2019) ViT (Dosovitskiy et al. 2021) Unified-IO (Lu et al. 2022) |
|
|
8 |
Mar 7 (Tues) |
Foundation Models: CLIP and GPT-3 |
|
|
|
8 |
Mar 9 (Thurs) |
Exam 1 on PrairieLearn 9:30am to 10:30pm |
|
|
|
9 |
Mar 11-19 |
Spring Break (no classes) |
|
|
|
10 |
Mar 21 (Tues) |
Building ML Applications and Task Adaptation |
|
|
|
10 |
Mar 23 (Thurs) |
Ethics and Impact of AI |
|
|
|
11 |
Mar 27 (Mon) |
HW 3 (Application Domains) due |
|
|
|
11 |
Mar 28 (Tues) |
Bias in AI, and Fair ML |
|
|
|
|
|
Pattern Discovery |
|
|
|
11 |
Mar 30 (Thurs) |
Clustering and Retrieval |
AML Ch 8 |
|
|
12 |
Apr 4 (Tues) |
EM and Latent Variables |
AML Ch 9 |
|
|
12 |
Apr 6 (Thurs) |
Density estimation: MoG, Hists, KDE |
AML Ch 9 |
|
|
13 |
Apr 11 (Tues) |
Dimensionality Reduction: PCA, embeddings |
AML Ch 11 |
|
|
13 |
Apr 13 (Thurs) |
Topic Modeling |
|
|
|
14 |
Apr 17 (Mon) |
HW 4 (Pattern Discovery) due |
|
|
|
14 |
Apr 18 (Tues) |
Outliers and Robust Estimation |
||
|
|
|
More Applications and Topics |
|
|
|
14 |
Apr 20 (Thurs) |
Reinforcement Learning (by Josh Levine) |
|
|
|
15 |
Apr 25 (Tues) |
Audio and 1D Signals |
||
|
16 |
Apr 27 (Thurs) |
ML Applications |
|
|
|
16 |
May 2 (Tues) |
Summary and Looking Forward |
|
|
|
16 |
May 3 (Wed) |
Final Project due (cannot be late) |
|
|
|
|
May 9 (Tues) |
Final Exam on PrairieLearn, May 9 9:30am to May 10 10:30am |
|