Georgia Institute of Technology

Course Syllabus: CS7643 Deep Learning

Spring 2021
Delivery: 100% Web-Based on Canvas, with submissions on Canvas/Gradescope
Dates course will run: January 14, 2021 – May 6, 2020

Instructor Information
Dr. Kira Zsolt
Email: [email protected]

General Course Information

Description
Deep learning is a sub-field of machine learning that focuses on learning complex, hierarchical feature
representations from raw data. The dominant method for achieving this, artificial neural networks, has
revolutionized the processing of data (e.g. images, videos, text, and audio) as well as decision-making tasks
(e.g. game-playing). Its success has enabled a tremendous amount of practical commercial applications and
has had a significant impact on society.

In this course, students will learn the fundamental principles, underlying mathematics, and implementation
details of deep learning. This includes the concepts and methods used to optimize these highly
parameterized models (gradient descent and backpropagation, and more generally computation graphs),
the modules that make them up (linear, convolution, and pooling layers, activation functions, etc.), and
common neural network architectures (convolutional neural networks, recurrent neural networks, etc.).
Applications ranging from computer vision to natural language processing and decision-making
(reinforcement learning) will be demonstrated. Through in-depth programming assignments, students will
learn how to implement these fundamental building blocks as well as how to put them together using a
popular deep learning library, PyTorch. In the final project, students will apply what they have learned to
real-world scenarios by exploring these concepts with a problem that they are passionate about.

Pre- &/or Co-Requisites

It is recommended that students have a strong mathematical background (linear algebra, calculus especially
taking partial derivatives, and probabilities & statistics) and at least an introductory course in Machine
Learning (e.g. equivalent to CS 7641). Strong programming skills (specifically Python) are necessary to
complete the assignments.

Course Objectives
● Describe the major differences between deep learning and other types of machine learning algorithms.
● Explain the fundamental methods involved in deep learning, including the underlying optimization
concepts (gradient descent and backpropagation), typical modules they consist of, and how they can be
combined to solve real-world problems.
● Differentiate between the major types of neural network architectures (multi-layered perceptions,
convolutional neural networks, recurrent neural networks, etc.) and what types of problems each is
appropriate for.
● Select or design neural network architectures for new data problems based on their requirements and
problem characteristics and analyze their performance.
● Describe some of the latest research being conducted in the field and open problems that are yet to be
solved.

1
Georgia Institute of Technology
Course Syllabus: CS7643 Deep Learning
Course Materials
Course Text
Deep Learning, by Ian Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press. Available online.

Additional Materials/Resources
All additional reading materials will be available via PDF on Canvas.

Course Website and Other Classroom Management Tools

All course materials and videos are located on Canvas.

Course Requirements, Assignments & Grading

Assignment Distribution and Grading Scale

Assignments Weight

On-Boarding Quiz (required to verify identity using proctoring

software)

Assignments (4) 55%

Quizzes 20%

Final Project (including proposal) 20%

Class Participation (Graded Discussions & 5%

Piazza Participation)

Grading Scale
Your final grade will be assigned as a letter grade, with at least the following grades (i.e. 90 or greater will
definitely be an A).
A 90-100%
B 80-89%
C 70-79%
D 60-69%
F 0-59%

Assignment Due Dates

All assignments are due at the day posted on Canvas, and at 11:59:00pm AOE on the date posted unless
otherwise noted. All assignments are due relative to Anywhere on Earth (AOE). We will not accept
assignments submitted late due to time zone issues. You should update your canvas to account for AOE if
you are in a different time zone. There are no exceptions.

Every homework deliverable, project deliverable, and discussion items will have a 48-hour grace period
during which no penalty will apply. There is no grace period for taking quizzes. This is intended for you as
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.

2
Georgia Institute of Technology
Course Syllabus: CS7643 Deep Learning

Late and Make-up Work Policy

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. 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/medial information to the
instructor or TAs; all such information should go through the Dean of Students.

Technology Requirements and Skills

Computer Hardware and Software
● High-speed Internet connection
● Laptop or desktop computer with a minimum of a 2 GHz processor and 4 GB of RAM
● Windows for PC computers OR Mac iOS for Apple computers.
● Complete Microsoft Office Suite or comparable and ability to use Adobe PDF software (install,
download, open and convert)
● Mozilla Firefox, Chrome browser, and/or Safari browsers (Chrome required for on-boarding quiz)

Canvas
This class will use Canvas to deliver course materials to online students. ALL course materials and
quiz/discussion assessments will take place on this platform. Gradescope will be used for submission of
assignments and the project.

Proctoring Information
In order to verify the identity of all GT online students, all online students are required to complete the
onboarding quiz that uses Honorlock. Honorlock is utilized for student identity verification and to ensure
academic integrity. Honorlock provides student identity verification via facial and ID photos. You may also
be asked to scan the room around you. The onboarding quiz will be a practice quiz that will not affect your
grade in the course. You can take the onboarding quiz as many times as you want. All potential violations are
reviewed by a human. The Honorlock support team is available 24/7. While Honorlock will not require you to
create an account, download software, or schedule an appointment in advance, you will need Google
Chrome and download the Honorlock Chrome Extension. Information on how to access Honorlock and
additional resources are provided below. You can also access Honorlock support
at https://honorlock.com/support/.

Course Policies, Expectations & Guidelines

Communication Policy
You are responsible for knowing the following information:
1. Anything posted to this syllabus
2. Anything emailed directly to you by the teaching team (including announcements via Piazza), 24
hours after receiving such an email or post.

Because Piazza announcements are emailed to you as well, you need only to check your Georgia Tech email
once every 24 hours to remain up to date on new information during the semester. Georgia Tech generally
recommends students to check their Georgia Tech email once every 24 hours. So, if an announcement or
message is time sensitive, you will not be responsible for the contents of the announcement until 24 hours

3
Georgia Institute of Technology
Course Syllabus: CS7643 Deep Learning
after it has been sent.

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

1. 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.
2. 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.
3. 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. ☺
4. Consider the privacy of others. Ask permission prior to giving out a classmate's email address or other
information.
5. 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).
6. 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.

University Use of Electronic Email

A university-assigned student e-mail account is the official university means of communication with all
students at Georgia Institute of Technology. Students are responsible for all information sent to them via
their university-assigned e-mail account. If a student chooses to forward information in their university e-
mail account, he or she is responsible for all information, including attachments, sent to any other e-mail
account. To stay current with university information, students are expected to check their official university
e-mail account and other electronic communications on a frequent and consistent basis. Recognizing that
some communications may be time-critical, the university recommends that electronic communications be
checked minimally twice a week.

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
http://www.catalog.gatech.edu/policies/honor-code/ or http://www.catalog.gatech.edu/rules/18/.

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.
Any public material that you use (open-source software, help from a textbook, or substantial help from a
4
Georgia Institute of Technology
Course Syllabus: CS7643 Deep Learning
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 a quiz, exam, or assignment will be reported to the Office of
Student Integrity, who will investigate the incident and identify the appropriate penalty for violations.

Accommodations for 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 http://disabilityservices.gatech.edu/, 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.

Student-Faculty Expectations Agreement

At Georgia Tech we believe that it is important to strive for an atmosphere of mutual respect,
acknowledgement, and responsibility between faculty members and the student body. See
http://www.catalog.gatech.edu/rules/22/ for an articulation of some basic expectation that you can have of
me and that I have of you. In the end, simple respect for knowledge, hard work, and cordial interactions will
help build the environment we seek. Therefore, I encourage you to remain committed to the ideals of
Georgia Tech while in this class.

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.

5
Georgia Institute of Technology
Course Syllabus: CS7643 Deep Learning
Course Schedule
Week/Dates Modules/Lessons Deliverables

1 Module 1: Introduction to Neural Networks 1

Weeks of Go through Welcome/Getting Started
January 11 & Lesson 1: Linear Classifiers and Gradient
January 18 Descent
Readings:
(Note: Semester  DL book: Linear Algebra background
starts Jan. 14)  DL book: Probability background
 DL book: ML Background
 LeCun et al., Nature '15
 Shannon, 1956
2 Lesson 2: Neural Networks Quiz #1: Linear Classifiers and Gradient
January 25 Readings: Descent (Lesson 1) and Neural Networks
(Lesson 2) Due Jan. 31 11:59pm AOE (no
 DL book: Deep Feedforward Nets grace period!)
 Matrix calculus for deep learning
 Automatic Differentiation Survey, Baydin et
al.

3 Lesson 3: Optimization of Deep Neural Assignment 1 Due Feb. 7 11:59pm AOE

February 1 Networks (grace period until Feb. 9)
Readings:
 DL book: Regularization for DL
 DL book: Optimization for Training Deep
Models

4 Lesson 4: Data Wrangling Quiz #2: Optimization of Deep Neural

February 8 Module 2: Convolutional Neural Networks Networks (Lesson 3), Data Wrangling
(Lesson 4), and Convolution and Pooling
Lesson 5: Convolution and Pooling Layers Layers (Lesson 5) Due Feb. 14 11:59pm
Readings: AOE (no grace period!)
 General preprocessing: Preprocessing for
deep learning: from covariance matrix to
Graded Discussion 1 Due Feb. 14
image whitening
11:59pm AOE (grace period until Feb.
 General preprocessing: cs231n on
preprocessing 16)
 DL book: Convolutional Networks
 Optional: Khetarpal, Khimya, et al. Re-
evaluate: Reproducibility in evaluating
reinforcement learning algorithms." (2018).
See related blog post

5 Lesson 6: Convolutional Neural Network

February 15 Architectures

6
Georgia Institute of Technology
Course Syllabus: CS7643 Deep Learning
Week/Dates Modules/Lessons Deliverables

6 Lesson 7: Visualization Assignment 2 Due Feb. 28 11:59pm

February 22 Lesson 8: PyTorch and Scalable Training AOE (grace period until Mar. 2)
Readings:
 Understanding Neural Networks
Through Deep Visualization
 Grad-CAM: Visual Explanations from
Deep Networks via Gradient-based
Localization

7 Lesson 9: Advanced Computer Vision Quiz #3: Convolutional Neural Network

March 1 Architectures Architectures (Lesson 6), Visualization
Lesson 10: Bias and Fairness (Lesson 7), Advanced Computer Vision
Architectures (Lesson 9), and Bias and
Readings: Fairness (Lesson 10) Due March 7
 Fully Convolutional Networks for 11:59pm AOE (no grace period)
Semantic Segmentation

Graded Discussion 2 (M2) Due March 7

11:59pm AOE (grace period until Mar.
9)

8 Module 3: Structured Neural Assignment 3 Due March 14 11:59pm

March 8 Representations AOE (grace period until Mar. 16)
Lesson 11: Introduction to Structured
Representations
Lesson 12: Language Models
Readings:
 DL Book: Sequential Modeling and
Recurrent Neural Networks (RNNs)

9 Lesson 13: Embeddings Project Proposal Due March 21

March 15 11:59pm AOE (grace period until Mar.
23)
Readings:
 word2vec tutorial
 word2vec paper Quiz #4: Structured Representations
 StarSpace paper (Lesson 11). Language Models (Lesson
12, and Embeddings (Lesson 13) Due
March 21 11:59pm AOE (no grace
period)

(March 17 Withdrawal Deadline)

10 Lesson 14: Neural Attention Models

7
Georgia Institute of Technology
Course Syllabus: CS7643 Deep Learning
Week/Dates Modules/Lessons Deliverables
March 22
Readings:
 Attention is all you need (Links to an
external site.)
 BERT Paper (Links to an external site.)
 The Illustrated Transformer

11 Lesson 15: Neural Machine Translation Quiz #5: Neural Attention Models
March 29 Lesson 16: Advanced Topics (Lesson 14), Neural Machine Translation
(Lesson 15), and Advanced Topics
(Lesson 16) Due April 4 11:59pm AOE
(no grace period)

Assignment 4 Due April 4 11:59pm AOE

(grace period until Apr. 6)

12 Module 4: Advanced Topics Graded Discussion 3 (M3) Due April 11

April 5 Lesson 17: Deep Reinforcement Learning 11:59pm AOE (grace period until Apr.
13)
Readings:
 MDP Notes (courtesy Byron Boots)
 Notes on Q-learning (courtesy Byron
Boots)
 Policy iteration notes (courtesy
Byron Boots)
 Policy gradient notes (courtesy
Byron Boots)

13 Lesson 18: Unsupervised and Semi- Quiz #6: Deep Reinforcement Learning
April 12 Supervised Learning (Lesson 17) and Unsupervised and Semi-
Supervised Learning (Lesson 18) Due
April 18 11:59pm AOE (no grace period)

14 Lesson 19: Generative Models Quiz #7: Generative Models (Lesson 19)
April 19 Readings: Due April 25 11:59pm AOE (no grace
period)
 Tutorial on Variational Autoencoder
 NIPS 2016 Tutorial: Generative
Adversarial Networks

15 Wrap-Up Final Project Due May 4th 11:59pm AOE

April 26 Graded Discussion 4 (M4) Due May 6th
11:59pm AOE
8
Georgia Institute of Technology
Course Syllabus: CS7643 Deep Learning