|
Instructor: Derek Hoiem Lectures:
Tues/Thurs 12:30-1:45, 0027/1025 CIF Lecture
Recordings, ClassTranscribe Lecture
Review Questions
and Answers CampusWire
Discussion (sign-up
link/code: 9325) Canvas Submission (gradescope code: RV8DEW) Textbook: Applied
Machine Learning by David Forsyth Assignments HW
1 – Instance-based Methods (Sep 14) HW 2
– PCA and Linear Models (Sep 28) HW 3
– PDFs and Outliers (Oct 12) HW 4
– Trees and MLPs (Nov 2) HW 5
– Deep Learning and Applications (Nov 16) Final
Project (Dec 13) |
|
Class Schedule (subject to change)
|
Date |
Topic |
Link |
Reading/Notes |
|
Aug 25 (Tues) |
Introduction |
||
|
|
Fundamentals of Learning |
|
|
|
Aug 27 (Thurs) |
K-NN Classification, Data Representation |
|
AML Ch 1.1-1.2 |
|
Probability/Background
Review (ask to review in office hours for individual help) |
|||
|
Sep 1 (Tues) |
K-NN Regression, Generalization |
|
AML Ch 1.1-1.2 |
|
Sep 3 (Thurs) |
Search and Clustering |
|
AML Ch 8 |
|
Sep 8 (Tues) |
Dimensionality reduction:
PCA, embeddings No in-person lecture,
recording only |
AML Ch 5, 6, 19 |
|
|
Sep 10 (Thurs) |
Linear regression,
regularization No in-person lecture, recording only |
AML Ch 10-11 |
|
|
Sep 14 (Mon) |
HW 1 (Instance-based Methods) due |
|
|
|
Sep 15 (Tues) |
Linear classifiers: logistic regression, SVM |
|
AML Ch 11.3, 2.1 |
|
Sep 17 (Thurs) |
Naïve Bayes Classifier |
|
AML Ch 2 |
|
Sep 22 (Tues) |
EM and Latent Variables |
|
AML Ch 9 |
|
Sep 24 (Thurs) |
Density estimation: MoG, Hists, KDE |
|
AML Ch 9 |
|
Sep 28 (Mon) |
HW 2 (PCA and Linear
Models) due |
|
|
|
Sep 29 (Tues) |
Outliers and Robust Estimation |
|
|
|
Oct 1-4 |
Exam 1 at CBTF Optional review on Oct 1 in
lecture |
|
practice questions
; ref sheet |
|
Oct 6 (Tues) |
Decision Trees |
|
AML Ch 2 |
|
Oct 8 (Thurs) |
Ensembles and Random Forests |
|
AML Ch 2 |
|
|
Deep Learning |
|
|
|
Oct
12 (Mon) |
HW 3 (PDFs and Outliers) |
|
|
|
Oct 13 (Tues) |
Stochastic Gradient Descent |
|
AML Ch 2.1; Pegasos (Shalev-Shwartz et al. 2007) |
|
Oct 15 (Thurs) |
MLPs and Backprop |
|
AML 16 |
|
Oct 20 (Tues) |
CNNs and Keys to Deep Learning |
|
AML Ch 17-18, ResNet
(He et al. 2016) |
|
Oct 22 (Thurs) |
Deep Learning Optimization and Computer Vision |
|
|
|
Oct 27 (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 29 (Thurs) |
Transformers in Language and Vision |
|
BERT (Devlin et al. 2019) ViT (Dosovitskiy et al. 2021) Unified-IO (Lu et al. 2022) |
|
Nov 2
(Mon) |
HW 4 (Trees and MLPs) due |
|
|
|
Nov 3 (Tues) |
Foundation Models: CLIP and GPT |
|
CLIP (Radford et al. 2021) |
|
Nov 5-8 |
Exam 2 at CBTF
(Optional review on Nov 5) |
|
|
|
|
Applications |
|
|
|
Nov 10 (Tues) |
Ethics and Impact of AI |
|
|
|
Nov 12 (Thurs) |
Bias in AI, Fair ML |
|
|
|
Nov 16 (Mon) |
HW 5 (Deep Learning and
Applications) due |
|
|
|
Nov 17 (Tues) |
Building and Deploying ML Guest speaker: Chenxi
Yu (State Farm) |
|
(no slides) |
|
Nov 19 (Thurs) |
Audio and 1D Signals |
|
|
|
Nov 21-Nov 29 |
Fall Break |
|
|
|
Dec 1 (Tues) |
Reinforcement Learning |
|
|
|
Dec 3 (Thurs) |
Review, summary, looking forward |
|
|
|
Dec 8 (Tues) |
No Class – Office
hours for Final Project in Lecture Hall (CIF 0027) 12:30-1:30 |
|
|
|
Dec 3-8 |
Exam 3 at CBTF |
|
practice
questions; ref sheet |
|
Dec 13 (Sun) |
Final Project due (cannot be late) |
|
|