CS 7643 Deep Learning

CS 7643 Deep Learning
CS 4644 / 7643 Deep Learning
Please visit
this site
for the latest iteration of the course (Fall 2024)
Fall 2022, Tue/Thu 12:30 pm - 1:45 pm, Paper Tricentennial 109
Course Information
Schedule
Grading
Late Policy
Prerequisites
FAQs
Projects
External Resources
Course Information
This is an exciting time to be studying (Deep) Machine Learning, or Representation Learning, or for lack of a better term, simply Deep Learning!
Deep Learning is rapidly emerging as one of the most successful and widely applicable set of techniques across a range of domains
(vision, language, speech, reasoning, robotics, AI in general), leading to some
pretty
significant
commercial
success
and
exciting
new
directions
that may previously have seemed out of
reach
This course will introduce students to the basics of Neural Networks (NNs) and expose them to some cutting-edge research.
It is structured in modules (background, Convolutional NNs, Recurrent NNs, Deep Reinforcement Learning, Deep Structured Prediction).
Modules will be presented via instructor lectures and reinforced with homeworks that teach theoretical and practical
aspects. The course will also include a project which will allow students to explore an area of Deep Learning that interests them in more depth.
Instructor
Danfei Xu
Teaching Assistants
Head TA: Adi Singh
Anshul Ahluwalia
Amogh Dabholkar
Charlie Gunn
Anshul Gupta
Yash Jakhotia
Hoon Lee
Zach Minot
Aaditya Singh
Ningyuan Yang
Class Info & Links
Lectures: Tue/Thu 12:30 pm - 1:45 pm, Paper Tricentennial 109
Piazza:
(code available on Canvas)
Canvas
CS4644:
CS7643:
Gradescope
CS4644:
CS7643:
Tentative Schedule (subject to changes)
Date
Topic
Optional Reading
W1: Aug 23
Intro lecture + class logistics.
Slides (pdf)
PS0
is due 11:59pm 08/30 (NO grace period).
IMPORTANT: All students MUST complete PS0! This is true even if you are currently on the waitlist and likely to get in! See FAQ below for gradescope access if you are not registered.
LeCun et al., Nature '15
Shannon, 1956
DL book: Linear Algebra background
DL book: Probability background
DL book: ML Background
W1: Aug 25
Machine learning intro, applications (CV, NLP, etc.), parametric models and their components
Slides (PDF)
W2: Aug 30
Supervised Learning, Linear Classification, Loss functions, Gradient Descent
Slides (pdf)
PS0 due 08/30 11:59pm EST.
DL book: Linear Algebra background
DL book: Probability background
DL book: ML Background
W2: Sep 1
Backpropagation, Computation Graph
PS1 out
Slides (pdf)
W3: Sep 6
Backpropagation with Neural Networks. Optimization Basics
Slides (pdf)
HW1 out
DL book: Deep Feedforward Nets
Matrix calculus for deep learning
Automatic Differentiation Survey, Baydin et al.
W3: Sep 8
How to Pick a Project
Slides (pdf)
W4: Sep 13
Convolution
Slides (pdf)
DL book: Convolutional Networks
W4: Sep 15
Convolution, Pooling, Convolutional Neural Networks
Slides (pdf)
PS/HW1 due Sep. 19th 11:59pm, PS/HW2 out on Sep. 19th
DL book: Convolutional Networks
W5: Sep 20
Convolutional Neural Networks
Slides (pdf)
DL book: Convolutional Networks
W5: Sep 22
Training Neural Networks 1: Activation Functions, Data Preprocessing, Weight Initialization
Slides (pdf)
General preprocessing:
cs231n on preprocessing
General preprocessing:
Preprocessing for deep learning: from covariance matrix to image whitening
W6: Sep 27
Training Neural Networks 2: Batch Normalization, Optimization, Regularization
Slides (pdf)
Project Proposal Due Sep 27th 11:59pm
DL book: Regularization for DL
DL book: Optimization for Training Deep Models
W6: Sep 29
Training Neural Networks 3: Data Augmentation, Hyperparameter Search, Transfer Learning, Model Ensembles
Slides (pdf)
W7: Oct 4
Deep Learning Software and Hardware
Slides (pdf)
W7: Oct 6
Computer Vision: Detection and Segmentation
Slides (pdf)
PS/HW2 due Oct 10th 11:59pm, PS/HW3 out
Fully Convolutional Networks for Semantic Segmentation
W8: Oct 11
Visualizing Neural Networks
Slides (pdf)
Understanding Neural Networks Through Deep Visualization
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
W8: Oct 13
Recurrent Neural Networks, Long Short-Term Memory
Slides (pdf)
W9: Oct 18
Fall Break - No Class
W9: Oct 20
Attentions and Transformers
Slides (pdf)
Attention is all you need
BERT Paper
The Illustrated Transformer
Formal Algorithms for Transformers
W10: Oct 25
Zoom only, no in-person lecture
Embodied Reasoning Through Planning with Language and Vision Foundation Models.
Guest Lecture by
Fei Xia
, Google Research
PS/HW3 due Oct 25th 11:59pm, PS/HW4 out
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
W10: Oct 27
Zoom only, no in-person lecture
Building Intelligent Machines that Learn from Human Speech
Guest Lecture by
Michael Auli
, Meta Research
W11: Nov 1
Generative Models - Autoregressive Models and Variational Autoencoders (VAE)
Slides (pdf)
W11: Nov 3
Generative Models - Denoising Diffusion Probablistic Models
Slides (pdf)
Milestone Report Due Nov 3 11:59pm
W12: Nov 8
Zoom only, no in-person lecture
Natural Language Processing: Language Models and Foundation Models
Guest Lecture by
Siddharth Karamcheti
, Stanford University
W12: Nov 10
Reinforcement Learning 1: MDP, Value Iteration, Deep Q Learning.
PS/HW4 due Nov 11th 11:59pm
Slides (pdf)
Sutton & Bartow Chapter 1
Survey paper on Deep RL
MDP Notes (courtesy Byron Boots)
W13: Nov 15
Reinforcement Learning 2: Actor-Critic, Frontiers.
Slides (pdf)
Sutton & Bartow Chapter 1
Survey paper on Deep RL
MDP Notes (courtesy Byron Boots)
W13: Nov 17
No Class
W14: Nov 22
Zoom only, no in-person lecture
AI Alignment and Safety
Guest Lecture by
Rohin Shah
, DeepMind
W14: Nov 24
Thanksgiving Holiday - No Class
W15: Nov 29
Self-Supervised Learning
Slides (pdf)
W15: Dec 1
Robot Learning and Emerging Trend, wrap up
Final Project Due Dec 4th 11:59pm
W16: Dec 6
Poster Session (Klaus Atrium)
Grading
64% Homework (4 homeworks)
36% Final Project
1% (potential bonus) Class Participation: top endorsed answers/questions/comments on Piazza
Late policy for deliverables
There will be no make-up work provided for missed assignments. Of course, emergencies (illness, family emergencies) will happen. In those instances, please contact the
Dean of Students
office (see
here
for rules). The Dean of Students is equipped to verify emergencies and pass confirmation on to all your classes. For consistency, we ask all students to do this in the event of an emergency. Do not send any personal/medical information to the instructor or TAs; all such information should go through the Dean of Students.
Every homework deliverable and project deliverable will have a 48-hour grace period during which no penalty will apply. This is intended to allow you time to verify that your submission has been submitted (we recommend you re-download it and look it over to make sure all questions/deliverables have been answered). Canvas will show your submission as late, but you do not have to ask for this grace period. Deliverables after the grace period will receive a grade of 0.
Prerequisites
CS 4644/7643 should NOT be your first exposure to machine learning. Ideally, you need:
Intro-level Machine Learning
CS 3600 for the undergraduate section and CS 7641/ISYE 6740/CSE 6740 or equivalent for the graduate section.
Algorithms
Dynamic programming, basic data structures, complexity (NP-hardness)
Calculus and Linear Algebra
positive semi-definiteness, multivariate derivates (be prepared for lots and lots of gradients!)
Programming
This is a demanding class in terms of programming skills.
HWs will involve Python and PyTorch.
Your library of choice for project.
Ability to deal with abstract mathematical concepts
Online Student Conduct and (N)etiquette
Communicating appropriately in the online classroom can be challenging. All communication, whether by email, Piazza, Canvas, or otherwise, must be professional and respectful. In order to minimize this challenge, it is important to remember several points of “internet etiquette” that will smooth communication for both students and instructors
Read first, Write later. Read the ENTIRE set of posts/comments on a discussion board before posting your reply, in order to prevent repeating commentary or asking questions that have already been answered.
Avoid language that may come across as strong or offensive. Language can be easily misinterpreted in written electronic communication. Review email and discussion board posts BEFORE submitting. Humor and sarcasm may be easily misinterpreted by your reader(s). Try to be as matter of fact and as professional as possible.
Follow the language rules of the Internet. Do not write using all capital letters, because it will appear as shouting. Also, the use of emoticons can be helpful when used to convey nonverbal feelings. ☺
Consider the privacy of others. Ask permission prior to giving out a classmate’s email address or other information.
Keep attachments small. If it is necessary to send pictures, change the size to an acceptable 250kb or less (one free, web-based tool to try is picresize.com).
No inappropriate material. Do not forward virus warnings, chain letters, jokes, etc. to classmates or instructors. The sharing of pornographic material is forbidden.
NOTE: The instructor reserves the right to remove posts that are not collegial in nature and/or do not meet the Online Student Conduct and Etiquette guidelines listed above.
Plagiarism & Academic Integrity
Georgia Tech aims to cultivate a community based on trust, academic integrity, and honor. Students are expected to act according to the highest ethical standards. All students enrolled at Georgia Tech, and all its campuses, are to perform their academic work according to standards set by faculty members, departments, schools and colleges of the university; and cheating and plagiarism constitute fraudulent misrepresentation for which no credit can be given and for which appropriate sanctions are warranted and will be applied. For information on Georgia Tech’s Academic Honor Code, please visit
or
You are encouraged to discuss problems and papers with others as long as this does not involve the copying of code or solutions. After discussions, all materials that are part of a submission should be wholly your own. Do NOT search for code directly implementing the assignment and submit snippets or variations of them. You can search for conceptual information but NOT code solutions. Any public material that you use (open-source software, help from a textbook, or substantial help from a friend, etc.) should be acknowledged explicitly in anything you submit to us. If you have any doubts about whether something is legal or not, please do check with the class Instructor or the TA.
We will actively check for cheating, and any act of dishonesty will result in a Fail grade. Any student suspected of cheating or plagiarizing on any deliverable including assignments will be reported to the Office of Student Integrity, who will investigate the incident and identify the appropriate penalty for violations.
Students with Disabilities
If you are a student with learning needs that require special accommodation, contact the Office of Disability Services at 404.894.2563 or
, as soon as possible, to make an appointment to discuss your special needs and to obtain an accommodations letter. Please also e-mail me as soon as possible in order to set up a time to discuss your learning needs.
Subject to Change Statement
The syllabus and course schedule may be subject to change. Changes will be communicated via the Canvas announcement tool. It is the responsibility of students to check Piazza, email messages, and course announcements to stay current in their online courses.
Campus Resources
Community Resources
Project Details (36% of course grade)
The class project is meant for students to (1) gain experience implementing
deep models and (2) try Deep Learning on problems that interest them. The
amount of effort should be at least the level of 1.5 homework assignment per
group member (2-4 people per group). The deliverables are
- Project Proposal (1%): Due Sep 27
- Milestone Report (5%): Due Nov 1
- Final Report (25%): Due Dec 4
- Poster Session (5%): Dec 6, Klaus Atrium
The final report is a PDF write-up describing the project in a self-contained manner will be the sole
deliverable. Your final write-up is required to be between 4 - 6 pages using the
template
here
structured like a paper from a computer vision conference
(CVPR, ECCV, ICCV, etc.). Please use this template so we can fairly judge all student
projects without worrying about altered font sizes, margins, etc. After the class, we
will post all the final reports online so that you can read about each others’ work.
Additionally, we will allow people to upload additional code, videos, and other supplementary material
as zip file similar to code upload for assignments.
While the PDF may link to supplementary material, external documents, and code,
such resources may or may not be used to evaluate
the project. The final PDF should completely address all of the points in the
rubric described below.
Rubric
We will release a detailed project rubric and the poster session format soon.
FAQs
The class is full. Can I still get in?
Sorry. The course admins in CoC control this process. Please talk to them.
Unregistered Students who intend to register:
If you are not registered for this course, you will not have access to Gradescope for submission of PS0. Please fill the following form in order to be added to Gradescope and be able to submit PS0:
Students who individually emailed us and have not been added yet - you may have left out the details of which course instance you are planning to take (either CS 7643 or CS 4644). There are two separate Gradescope courses for the two instances. Please fill the above form in order to provide us with this information.
Registered students who are not able to access Gradescope:
This will happen if you were registered to the course very recently. Gradescope rosters are synced periodically and it may take some time for you to receive a Gradescope sign-up notification. If you still face problems with accessing Gradescope, please email us.
I am graduating this Fall and I need this class to complete my degree requirements. What should I do?
Talk to the advisor or graduate coordinator for your academic program. They are keeping track of your degree requirements and will work with you if you need a specific course.
Can I audit this class or take it pass/fail?
No. Due to the large demand for this class, we will not be allowing audits or pass/fail. Letter grades only. This is to make sure students who want to take the class for credit can.
I have a question. What is the best way to reach the course staff?
Registered students – your first point of contact is Piazza (so that other students may benefit from your questions and our answers).
If you have a personal matter, create a private piazza post.
Related Classes / Online Resources
CS231n Convolutional Neural Networks for Visual Recognition, Stanford
Machine Learning, Oxford
Deep Learning, New York University
Deep Learning, CMU
Deep Learning, University of Maryland
Hugo Larochelle’s Neural Networks class
Book
Deep Learning, Ian Goodfellow, Aaron Courville, and Yoshua Bengio, MIT Press
Overviews
Deep Learning, Yann LeCun, Yoshua Bengio, and Geoffrey Hinton, Nature
Representation Learning: A Review and New Perspectives, Yoshua Bengio, Aaron Courville, and Pascal Vincent
Note to people outside Georgia Tech
Feel free to use the slides and materials available online here.
If you use our slides, an appropriate attribution is requested.
Please email the instructor with any corrections or improvements.