Machine Learning

CS-GY 6923, Fall 2024 at NYU

Lectures: Fridays at 2:00-4:30pm

Location: Jacobs Academic Bldg, Room 473, Brooklyn Campus

Instructor

Teaching Assistants

Adith Santosh

at6115@nyu.edu

Marc Chiu

mmc9967@nyu.edu

nk3696@nyu.edu

Prajjwal Bhattarai

pb2276@nyu.edu

Usaid Malik

uhm202@nyu.edu

How to get started:

  • Read the syllabus.
  • Join our Ed Discussion message board and Gradescope with the email invitations you received earlier this week. If you didn’t receive an email, you can use access code Z3GWBN for Gradescope (the link above for Ed Discussion will automatically let you join the class without a code).

Week 1

Sep 06
LEC 01 Introduction, Loss Functions, Simple Linear Regression
PDF   
Marked-PDF
Demo 01 Numpy, arrays, and plotting
Link   
Demo 02 Simple regression example
Link   
Sep 07
Lab 01 Release
Link   
Due: Sep16, 11:59pm
Reading
Probability Review
Notes by A. Maleki and T. Do   
Khan Academy
Linear Algebra Review
Note
Computing Gradient
Notes by Chris Musco   
Raw Markdown
Additional Reading
Ch. 3.1, 3.2 in An Introduction to Statistical Learning

Week 2

Sep 13
LEC 02 Multiple Linear Regression, Polynimial Regression, Model Selection
PDF   
Marked-PDF
Demo 03 Multiple Regression
Link   
Demo 04 Polynimial Regression, Model Order Selection
Link   
Sep 14
Lab 02 Release
Link   
Due: Sep24, 11:59pm
Reading
Computing Gradient
Notes by Chris Musco   
Raw Markdown
Regularization
Caltech Lecture 12

Week 3

Sep 18
HW 01 posted
PDF   
Solution   
LaTeX   
Due: Oct 01, 11:59pm
Sep 20
LEC 03 Naive Bayes
PDF   
Marked-PDF
Reading
Regularization
Caltech Lec 12      
Chapter 6.2 in AISL
Naive Bayes
Additional Lecture Notes

Week 4

Sep 27
LEC 04 Bayesian Machine Learning, Modeling Language
PDF   
Marked-PDF
Sep 28
Lab 03 Release
Link   
Due: Oct 08, 11:59pm
Reading
Bayes regression
Note on Least Squares Regression from a statistical perspective

Week 5

Oct 03
HW 02 posted
PDF   
Solution   
LaTeX   
Due: Oct 15, 11:59pm
Oct 04
LEC 05 KNN, Logistic Regression, Optimization
PDF   
Marked-PDF
Demo 05 Logistic regression
Link   
Reading
Logistic regression
Chapter 4.1-4.3 in AISL     
Note on Least Squares Regression

Week 6

Oct 11
LEC 06 (Stochastic) Gradient Descent
PDF   
Marked-PDF

Week 7

Oct 18
Midterm 01
Sample   
Solution  
info

Week 8

Oct 25
LEC 07 Learning Theory, the PAC model
PDF   
Marked-PDF
Oct 26
Lab 04 Release
Link   
Due: Nov 05, 11:59pm
Reading
PAC Learning
Note from Nika Haghtalab
VC dimension
Note from Nika’s course
More on VC dimention and Rademacher complexity
Book Chapters 6 and 26

Week 9

Nov 01
LEC 08 Kernel Methods, Support Vector Machines
PDF   
Marked-PDF
Demo 06 SVM for MNIST Digit Recognition
Link   
Reading
SVM’s additional reading
Chapter 9 in An Introduction to Statistical Learning.

Week 10

Nov 07
Lab 05 Release
Link   
Due: Nov 19, 11:59pm
HW 03 posted
PDF   
Solution   
LaTeX   
Due: Dec 02, 11:59pm
Nov 08
LEC 09 Neural Networks and Backpropagation
PDF   
Marked-PDF
Demo 07 Keras NN on synthetic data
Link   
Demo 08 Keras NN on MNIST data
Link   
Nov 09
Reading
Tensorflow playground

Week 11

Nov 15
LEC 10 Convolution, Feature Extraction, Adversarial Examples
PDF   
Marked-PDF
Demo 08 CNN using Keras
Link   
Demo 09 Train a CNN for CIFAR-10
Link    To make sure Colab is using a GPU, click on the Runtime tab and then Change Runtime Environment. Select GPU under hardware acceleration.

Week 12

Nov 22
LEC 11 Auto-encoders, Principal Component Analysis,
PDF   
Marked-PDF

Week 13

Nov 25
HW 04 posted
PDF   
Solution   
LaTeX   
Due: Dec 09, 11:59pm
Nov 29
Thanksgiving

Week 14

Dec 06
LEC 12 Semantic embeddings, Image Synthesis
PDF   
Marked-PDF

Week 15

Dec 11
LEC 13 Self-supervised learning, what’s next?
PDF   
Marked-PDF
Dec 13
Reading Day

Finals Week

Dec 20
Final Exam
Location:   TBD
Time:          TBD