Instructors: Varsha Kishore and Justin Lovelace
Contact: vk352@cornell.edu or jl3353@cornell.edu
Office hours:
Varsha Kishore: 1:00-2:00pm on Tuesdays in Rhodes 406
Justin Lovelace: 9:00-10:00am on Thursdays in Rhodes 404
Lectures: Tuesday and Thursday from 2:55 to 4:10 pm.
Course staff office hours:
Anissa Dallmann: Mondays 4:30-5:30pm in Rhodes 400
Adhitya Polavaram: Mondays 5:30-6:30pm in Rhodes 412
Zach Ross: Wednesdays from 4:00-5:00pm in Statler 453
Dylan Van Bramer: Fridays from 11:30-12:30pm in Rhodes 400
Luke Kulm: Fridays from 12:10-1:00pm in Rhodes 574
Course overview: This class is an introductory course to deep learning. It covers the fundamental principles behind training and inference of deep networks, deep reinforcement learning, the specific architecture design choices applicable for different data modalities, discriminative and generative settings, and the ethical and societal implications of such models.
Prerequisites: Fundamentals of Machine Learning (CS4780 , ECE4200 , STCSI4740), Python fluency (CS1110), 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) and Gradescope (for HWs). 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 four components: homework, mid-term exam, project and participation.
There will be a number of homework assignments throughout the course, typically made available roughly one to two weeks before the due date. The homeworks will have both theoretical questions and programming questions.
To provide hands on learning with the methods we discuss in class and to get familiar with common ML frameworks, there will be a project. For the project, students will implement the method proposed an existing research paper and will try to reproduce the results in the paper.
There will be one mid-term exam for the class based on the material covered in the lectures.
Given that this is the pilot offering of the course, students are expected to play an active role in providing constructive feedback. The participation grade will be based on feedback provided for lectures and assignments. There will also be daily quizes at the start of class; these will only be graded for participation (the score does not matter).
Final grades are based on homework assignments, project, exam and participation.
Your final grade consists of:A tentative schedule is given below. It is quite possible the specific topics covered on a given day will change slightly. This schedule will be updated as necessary.
| Topic | Date | Lecture | References | Notes/assignments | |
|---|---|---|---|---|---|
| Week 1 | Basics | Jan 23 | Logistics + History | Slides |
|
| Jan 25 | Multi-Layer Perceptrons (MLPs); Backpropagation | DiDL (Ch. 4-5);
CS 4780 (Sp2023); Backprop; Tensorflow Playground |
Slides |
||
| Week 2 | Training Neural Networks | Jan 30 | Optimization | DiDL (Ch. 12) | Slides |
| Feb 1 | Regularization | DiDL (Ch. 3.7, 5.6, 8.5) | Slides; HW1 Released | ||
| Week 3 | Computer Vision | Feb 6 | Convolutional Neural Networks | DiDL (Ch. 7) | Slides |
| Feb 8 | Modern ConvNets | DiDL (Ch. 8) | Slides | ||
| Week 4 | Natural Language Processing | Feb 13 | Word Embeddings | DiDL (Ch. 9) | Slides |
| Feb 15 | Recurrent Neural Networks (RNNs) | Slides;HW1 Due; HW2 Released | |||
| Week 5 | Feb 20 | Attention; Transformers | DiDL (Ch. 11) | Slides | |
| Feb 22 | Large Language Models (LLMs) | Speech and Language Processing (Chp. 10-11) | Slides | ||
| Week 6 | Graphs | Feb 27 | FEB BREAK (No Class) | ||
| Feb 29 | Graph Neural Networks (GNNs) | Slides;HW2 Due; HW3 Released | |||
| Week 7 | Modern Vision Networks | Mar 5 | Vision Pre-Training (Supervised, Self-supervised) | Slides | |
| Mar 7 | Vision-Language Models | Slides;Project Proposal Due | |||
| Week 8 | Generative Models | Mar 12 | Discriminators; Generative Adversarial Networks (GANs) | Slides | |
| Mar 14 | U-Nets; Variational Autoencoders (VAEs) | Slides;HW3 Due; HW4 Released | |||
| Week 9 | Mar 19 | Diffusion Models | Slides | ||
| Mar 21 | Diffusion II | Slides | |||
| Week 10 | Midterm | Mar 26 | Midterm Jeopardy | HW4 Due (No new HW) | |
| Mar 28 | Midterm | ||||
| Week 11 | SPRING BREAK | Apr 2 | No Class | ||
| Apr 4 | No Class | ||||
| Week 12 | Reinforcement Learning | Apr 9 | RL Setup | Slides | |
| Apr 11 | Deep Q-Learning | Slides;HW5 Released | |||
| Week 13 | Apr 16 | Policy Gradient | Slides | ||
| Apr 18 | RL w/ Human Feedback (RLHF) | Slides | |||
| Week 14 | AI in Human Society | Apr 23 | Robustness; Bias; AI Safety | Slides | |
| Apr 25 | Interpretability; Legal Issues; Environmental Impacts | Slides;HW5 Due; HW6 Released | |||
| Week 15 | Final Projects | Apr 30 | Project Presentations | ||
| May 2 | Project Presentations | ||||
| Week 16 | May 7 | Project Presentations | HW6 Due |
While this course does not explicitly follow a specific textbook, there are useful references on many of the topics covered. Pointers to references will be provided here.
Cornell University provides a comprehensive set of mental health resources and the student group Body Positive Cornell has put together a flyer outlined the resources available.
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.
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.