Instructor: Wen Sun
Office hours: Thursdays 2 - 3 pm in Gates Hall 416b
Lectures: Tuesday and Thursday from 8:40 am to 9:55 am in Bailey Hall 101.
Course staff office hours:Canvas Calendar (location: Rhodes 503)
Course overview: The course provides an introduction to machine learning, focusing on supervised learning and its theoretical foundations. Topics include regularized linear models, boosting, kernels, deep networks, generative models, online learning, and ethical questions arising in ML applications.
Prerequisites: probability theory (e.g. BTRY 3080, ECON 3130, MATH 4710, ENGRD 2700), linear algebra (e.g. MATH 2940), calculus (e.g. MATH 1920), and programming proficiency (e.g. CS 2110).
Course logistics: For enrolled students the companion Canvas page serves as a hub for access to Ed Discussions (the course forum), Vocareum (for course projects), Gradescope (for HWs), and paper comprehension quizzes. If you are enrolled in the course you should automatically have access to the site. Please let us know if you are unable to access it.
Your grade in this course is comprised of three components: homework, exams, and projects. Please also read through the given references in concert with the lectures.
There will be a number of homework assignments throughout the course, typically made available roughly one to two weeks before the due date. The homework primarily focuses on theoretical aspects of the material and is intended to provide preparation for the exams. Homework may be completed in groups of up to three. The assignments themselves will be made available via Gradescope (through Canvas). You are allowed two slip days per homework.
To provide hands on learning with the methods we will discuss in class there are a number of programming projects throughout the course. The projects may be completed solo or in a group of two. They are accessed, submitted, and graded using Vocareum. You are allowed two slip days per project.
Students enrolled in this course at the graduate level (i.e., enrolled in 5780) are required to read assigned research papers and complete the associated online quiz. Papers will be assigned roughly once every two to three weeks. You are allowed two slip days per quiz.
There will be two exams for this class, an evening prelim and a final exam.
Final grades are based on homework assignments, programming projects, and the exams. For the 5780 level version of the course the research comprehension quizzes will also factor in.For CS 4780 your final grade consists of:
Undergraduates enrolled in 4780 may choose to do the paper comprehension assignments; if completed you will receive the higher of your two grades between the above schemes.
A tentative schedule follows, and includes the topics we will be covering, relevant reference material, and assignment information. It is quite possible the specific topics covered on a given day will change slightly. This is particularly true for the lectures in the latter part of the course, and this schedule will be updated as necessary.
|8/22||Introduction||Slides PML: 1.1; ESL: Ch. 1; and PPA: Ch. 1|
|8/24||ML Basics||Slides, Annotated Slides, Lecture note PML: 1.2, and ESL: 2.1 and PPA: Ch. 1|
|8/29||K Nearest Neighbors and the curse of dimensionality||Slides, Annotated Slides, Lectue note, PML: 16.1|
|8/31||Clustering: K-means||Slides, Annotated Slides, Lecture note, ESL: 14.3.6 and 14.3.7, and PML: 21.3|
|9/5||Principal Component Analysis||Slides, Annotated Slides,Lecture note, PML: 20.1, ESL: 14.5.1 and 14.5.2|
|9/7||The Perceptron||Slides, Annotated Slides, Lecture note, Wikipedia articlea|
|9/12||MLE and MAP||Slides, Annotated Slides, Lecture note, ESL: 8.2.2-8.3||Homework 1 due; Project 1 due|
|9/14||Naive Bays||Slides, Annotated Slides, Lecture note|
|9/19||Logistic Regression and Gradient descent||Slides, Annotated Slides,Lecture note on logistic regression, Lecture note on Optimization, ESL: 4.4, and PML: 10.1, 0.2, and 10.3|
|9/21||Adaptive Gradient methods||Slides, Lecture note on Optimization, PML: 8.1, 8.2, and 8.3||Homework 2 due|
|9/26||optimization (continued)||PML: 8.1, 8.2, 8.3, and 8.4 (specifically, see PML 8.4 for SGD)||Project 2 due|
|9/28||Linear regression||PML 11.1, 11.2,11.3; ESL 3.2|
|10/3||Support Vector Machine||Project 3 due|
|10/5||Empirical Risk Minimization||PML 4.3, 5.4||Homework 3 due|
|10/10||Fall break, no class|
|10/12||Midterm Jeopardy||Homework 4 due 10/14|
|10/17||Exam Review||Evening prelim|
|10/19||Bias and Variance Tradeoff|
|10/24||Bias and Variance Tradeoff and Model Selection||Project 4 due|
|10/26||Kernels, part 1||PML: 17.1|
|10/31||Kernels, part 2||PML: 17.3|
|11/2||Classification and regression trees, part 1||Homework 5 due; Project 5 due|
|11/7||Classification and regression trees, part 2|
|11/9||Ensemble Methods: Bagging & random forest|
|11/14||Ensemble Methods: Boosting||Project 6 due|
|11/16||Neural Network||Homework 6 due|
|11/21||Neural Network: backpropagation|
|11/23||Thanksgiving, no class|
|11/28||Neural networks: convolutional and residual layers||PML: 14.1, 14.2, 14.3||Project 7 due; Homework 7 due|
|11/30||Neural networks: transformers||PML: 15.4 and 15.5||Project 8 due and Homework 8 due 12/5|
|tdb||Final Exam||location and time tbd|
While this course does not explicitly follow a specific textbook, there are several that are very useful references to supplement the course.
You are encouraged to actively participate in class. This can take the form of asking questions in class, responding to questions to the class, and actively asking/answering questions on the online discussion board.
Students are free to share code and ideas within their stated project/homework group for a given assignment, but should not discuss details about an assignment with individuals outside their group. The midterm and final exam are individual assignments and must be completed by yourself.
Students are free to use AI tools (e.g., ChatGPT, GPT4) for a given assignment. Students must include a detailed description of how they use the AI tools in their submission. Such details include (but not limited to) what AI tools are used, what prompts are used, how the AI generated content is used in the assignment, etc. Note that while GPTs are great products of ML,these models can still generate incorrect answers (i.e., these models can hallucinate). Always use AI tools with caution.
The Cornell Code of Academic Integrity applies to this course.
In compliance with the Cornell University policy and equal access laws, we are available to discuss appropriate academic accommodations that may be required for student with disabilities. Requests for academic accommodations are to be made during the first three weeks of the semester, except for unusual circumstances, so arrangements can be made. Students are encouraged to register with Student Disability Services to verify their eligibility for appropriate accommodations.