HW 1 – Instance-based Methods (Feb 5)HW 2 – PCA and Linear Models (Feb 19)HW 3 – PDFs and Outliers (Mar 4)HW
4 – Trees and MLPs (Apr 1)
HW
5 – Deep Learning and Applications (Apr 15)
Final
Project (May 1)
|
|
|
|
|
|
Class Schedule (subject to change)
Week |
Date |
Topic |
Link |
Reading/Notes |
1 |
Jan 16 (Tues) |
Introduction |
||
|
|
Fundamentals of Learning |
|
|
1 |
Jan 18 (Thurs) |
Working with Data |
|
|
2 |
Jan 23 (Tues) |
Clustering and Retrieval (recording expired) |
AML Ch 8 |
|
2 |
Jan 25 (Thurs) |
K-NN Classification and Regression |
AML Ch 1.1-1.2 |
|
3 |
Jan 30 (Tues) |
Dimensionality reduction: PCA, embeddings |
AML Ch 5, 6, 19 |
|
3 |
Feb 1 (Thurs) |
Linear regression, regularization |
AML Ch 10-11 |
|
4 |
Feb 5 (Mon) |
HW 1 (Instance-based Methods) due |
|
|
4 |
Feb 6 (Tues) |
Linear classifiers: logistic regression, SVM |
AML Ch 11.3, 2.1 |
|
4 |
Feb 8 (Thurs) |
Probability and Naïve Bayes |
AML Ch 2 |
|
5 |
Feb 13 (Tues) |
EM and Latent Variables |
AML Ch 9 |
|
5 |
Feb 15 (Thurs) |
Density estimation: MoG, Hists, KDE |
AML Ch 9 |
|
6 |
Feb 19 (Mon) |
HW 2 (PCA and Linear
Models) due |
|
|
6 |
Feb 20 (Tues) |
Outliers and Robust Estimation |
||
6 |
Feb 22 (Thurs) |
Decision Trees |
AML Ch 2 |
|
7 |
Feb 27 (Tues) |
Ensembles and Random Forests |
AML Ch 2 |
|
|
|
Deep Learning |
|
|
7 |
Feb 29 (Thurs) |
Stochastic Gradient Descent |
AML Ch 2.1; Pegasos (Shalev-Shwartz et al. 2007) |
|
8 |
Mar
4 (Mon) |
HW 3 (PDFs and Outliers) |
|
|
8 |
Mar 5 (Tues) |
Principles of Learning + Review |
|
|
8 |
Mar 7 (Thurs) |
Exam 1 on PrairieLearn 9:30am to 10:30pm |
Covers through Feb 29 (plus review) |
|
9 |
Mar 9-17 |
Spring Break (no classes) |
|
|
10 |
Mar 19 (Tues) |
MLPs and Backprop |
AML 16 |
|
10 |
Mar 21 (Thurs) |
CNNs and Keys to Deep Learning |
AML Ch 17-18, ResNet
(He et al. 2016) Recording failed. Link is
most similar from last year. |
|
11 |
Mar 26 (Tues) |
Deep Learning Optimization and Computer Vision |
||
11 |
Mar 28 (Thurs) |
Words and Attention |
Sub-word Tokenization (Sennrich et al. 2016) Word2Vec (Mikolov
et al. 2013) Attention is all you need
(Vaswani et al. 2017) |
|
12 |
Apr 1 (Mon) |
HW 4 (Trees and MLPs) due |
|
|
12 |
Apr 2 (Tues) |
Transformers in Language and Vision |
BERT (Devlin et al. 2019) ViT (Dosovitskiy et al. 2021) Unified-IO (Lu et al. 2022) |
|
12 |
Apr 4 (Thurs) |
Foundation Models: CLIP and GPT-3 |
CLIP (Radford et al. 2021) |
|
|
|
Applications |
|
|
13 |
Apr 9 (Tues) |
Ethics and Impact of AI |
||
13 |
Apr 11 (Thurs) |
Bias in AI, Fair ML |
|
|
15 |
Apr 15 (Mon) |
HW 5 (Deep Learning and
Applications) due |
|
|
14 |
Apr 16 (Tues) |
Building and Deploying ML: Guest speaker Daniel Kang |
||
14 |
Apr 18 (Thurs) |
Audio and 1D Signals |
||
15 |
Apr 23 (Tues) |
Reinforcement Learning: Guest speaker TA Josh Levine |
||
16 |
Apr 25 (Thurs) |
Student ML Applications |
|
|
16 |
Apr 30 (Tues) |
Summary and Looking Forward |
|
|
16 |
May 1 (Wed) |
Final Project due (cannot be late) |
|
|
|
May 6-8 |
Final
Exam on PrairieLearn May 6 9:30am to May 8 10:30pm |
Covers
entire semester |