Applied Machine Learning (CS 441) – Fall 2024
Instructor: Derek Hoiem
Lectures: Tues/Thurs 9:30-10:45, 1320 DCL
Syllabus
Lecture Recordings, ClassTranscribe
Lecture Review Questions and Answers
CampusWire Discussion (sign-up link/code: 6106)
Canvas Submission (Gradescope code: YR2E43)
Textbook: Applied Machine Learning by David Forsyth
Assignments
HW 1 – Instance-based Methods (Sep 16)HW 2 – PCA and Linear Models (Sep 30)HW 3 – PDFs and Outliers (Oct 14)HW
4 – Trees and MLPs (Nov 4)
HW
5 – Deep Learning and Applications (Nov 18)
Final
Project (Dec 15)
|
|
|
|
|
|
|
Class Schedule (subject to change)
|
Date |
Topic |
Link |
Reading/Notes |
|
Aug 27 (Tues) |
Introduction |
||
|
|
Fundamentals of Learning |
|
|
|
Aug 29 (Thurs) |
K-NN Classification, Data Representation |
AML Ch 1.1-1.2 |
|
|
Sep 3 (Tues) |
K-NN Regression, Generalization |
AML Ch 1.1-1.2 |
|
|
Sep 5 (Thurs) |
Search and Clustering |
AML Ch 8 |
|
|
Sep 9 (Mon) |
Probability/Background
Review (9pm) |
||
|
Sep 10 (Tues) |
Dimensionality reduction: PCA, embeddings |
AML Ch 5, 6, 19 |
|
|
Sep 12 (Thurs) |
Linear regression, regularization |
AML Ch 10-11 |
|
|
Sep 16 (Mon) |
HW 1 (Instance-based Methods) due |
|
|
|
Sep 17 (Tues) |
Linear classifiers: logistic regression, SVM |
AML Ch 11.3, 2.1 |
|
|
Sep 19 (Thurs) |
Naïve Bayes Classifier |
AML Ch 2 |
|
|
Sep 24 (Tues) |
EM and Latent Variables |
AML Ch 9 |
|
|
Sep 26 (Thurs) |
Density estimation: MoG, Hists, KDE |
AML Ch 9 |
|
|
Sep 30 (Mon) |
HW 2 (PCA and Linear
Models) due |
|
|
|
Oct 1 (Tues) |
Outliers and Robust
Estimation Derek away Sept 27 to
Oct 5 for ECCV |
||
|
Oct 3-6 |
Exam 1 at CBTF Optional Q&A w/ TAs on
Oct 3 in lecture |
||
|
Oct 8 (Tues) |
Decision Trees |
AML Ch 2 |
|
|
Oct 10 (Thurs) |
Ensembles and Random Forests |
AML Ch 2 |
|
|
|
Deep Learning |
|
|
|
Oct
14 (Mon) |
HW 3 (PDFs and Outliers) |
|
|
|
Oct 15 (Tues) |
Stochastic Gradient Descent |
AML Ch 2.1; Pegasos
(Shalev-Shwartz et al. 2007) |
|
|
Oct 17 (Thurs) |
MLPs and Backprop |
AML 16 |
|
|
Oct 22 (Tues) |
CNNs and Keys to Deep Learning |
AML Ch 17-18, ResNet (He et al. 2016) |
|
|
Oct 24 (Thurs) |
Deep Learning Optimization and Computer Vision |
||
|
Oct 29 (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) |
|
|
Oct 31 (Thurs) |
Transformers in Language and Vision |
BERT (Devlin et al. 2019) ViT (Dosovitskiy et al. 2021) Unified-IO (Lu et al. 2022) |
|
|
Nov 4
(Mon) |
HW 4 (Trees and MLPs) due |
|
|
|
Nov 5 (Tues) |
Foundation Models: CLIP and GPT-3 |
CLIP (Radford et al. 2021) |
|
|
Nov 7-10 |
Exam 2 at CBTF
(Optional review on Nov 7) |
|
|
|
|
Applications |
|
|
|
Nov 12 (Tues) |
Ethics and Impact of AI |
||
|
Nov 14 (Thurs) |
Bias in AI, Fair ML |
|
|
|
Nov 18 (Mon) |
HW 5 (Deep Learning and
Applications) due |
|
|
|
Nov 19 (Tues) |
Audio and 1D Signals Guest speaker: Minje
Kim |
||
|
Nov 21 (Thurs) |
Building and Deploying ML Guest speaker: Chenxi
Yu (State Farm) |
|
(no slides) |
|
Nov 23-Dec 1 |
Fall Break |
|
|
|
Dec 3 (Tues) |
Reinforcement Learning |
||
|
Dec 5 (Thurs) |
Review, summary, looking
forward |
|
|
|
Dec 5-10 |
Exam 3 at CBTF |
|
|
|
Dec 15 (Sun) |
Final Project due (cannot be late) |
|
|