CIS4930/6930 Deep Learning for Computer Graphics Spring 2021

Categories

Course Description

Deep learning algorithms are prevalent in computer graphics: from convolutional neural networks (CNNs) for denoising rendered movie frames to Generative Adversarial Networks (GANs) for simulating facial animation. This course covers the fundamental theory  and application of AI algorithms in the context of computer graphics through  lectures, reading assignments and a semester long programming project. The course is open to both graduate and undergraduate students.

 

Course Objectives

This course covers the fundamental theory and application of AI algorithms in the context of computer graphics. Deep learning is prevalent in graphics: from convolutional neural networks (CNNs) for denoising movie frames to Generative Adversarial Networks (GANs) for simulating facial animation. Through lectures, reading assignments (current research papers), and a semester long programming project, students will learn fundamental concepts including: supervised and unsupervised learning, convolutional neural network architectures, backpropagation, autoencoders and fine-tuning, as well as applications like image denoising and GANs for video simulation and animation.

 

Professional Component (ABET):

Students will learn fundamental concepts for solving engineering problems related to deep learning. Students will apply mathematical concepts to develop AI algorithms in a semester long programming project.

 

Relation to Program Outcomes (ABET):

 Outcome

Coverage*

  1. An ability to identify, formulate, and solve complex engineering problems by applying principles of engineering, science, and mathematics

High

  1. An ability to apply engineering design to produce solutions that meet specified needs with consideration of public health, safety, and welfare, as well as global, cultural, social, environmental, and economic factors

  1. An ability to communicate effectively with a range of audiences

Medium

  1. An ability to recognize ethical and professional responsibilities in engineering situations and make informed judgments, which must consider the impact of engineering solutions in global, economic, environmental, and societal contexts

Medium

  1. An ability to function effectively on a team whose members together provide leadership, create a collaborative and inclusive environment, establish goals, plan tasks, and meet objectives

Medium

  1. An ability to develop and conduct appropriate experimentation, analyze and interpret data, and use engineering judgment to draw conclusions

High

  1. An ability to acquire and apply new knowledge as needed, using appropriate learning strategies

Medium

 

Instructor:
Corey Toler-Franklin
ctoler@cise.ufl.edu
CSE 332 (Lab CSE 319)
Office Hours:   TBD, Zoom conference

 

Teaching Assistant/Peer Mentor/Supervised Teaching Student:

Please contact through the Canvas website

  • TBD, Zoom conference

 

Course Pre-Requisites / Co-Requisites

Proficiency in a programming Language (Python and/or C++ recommended), COP 3530, MAS 3114 or 4105

 

Materials and Supply Fees

N/A

 
TEXTBOOK

Required

 

ISBN: 9780262035613

href=
Author: Ian Goodfellow, Yoshua Bengio and Aaron Courville,


Title: Deep Learning

Free online version
Online

 

SYLLABUS

CIS6930/4930 Fall2021 Syllabus
Date
Topic
Reading
Assignments
11-Jan
Introduction
course survey out
13-Jan
Machine Learning Basics
Goodfellow 5-5.2.0, 5.3
15-Jan
Machine Learning Basics
course survey due
18-Jan
Martin Luther King Jr. Day (no classes)
20-Jan
Neural Networks
Goodfellow 6, 6.1, 6.4, 14, 14.1, 14.9
22-Jan*
Neural Networks
Goodfellow 4.3, 5.9, 6.5
27-Jan
Course Project Discussion
course proj. out
29-Jan*
Convolutional Neural Networks
Goodfellow 9-9.3
course proj. part1 out
3-Feb
Python, Torch, CUDA, cuDNN, TensorFlow
5-Feb*
Python, Torch, CUDA, cuDNN, TensorFlow
8-Feb
Training, Testing, Fine-tuning
Goodfellow 15.2, 7.4
10-Feb
Training, Testing, Fine-tuning
12-Feb*
Traditional Machine Learning
Lowe 2004, Toler-Franklin 2010
15-Feb
Traditional Machine Learning
course proj. part2 out
17-Feb
Recurrent Neural Networks
Goodfellow 10-10.2.2, 10.10.1
course proj. part1 due
19-Feb*
Natural Language Processing
22-Feb
Deep Learning in Graphics: Recent Trends
24-Feb
Deep Learning in Graphics
Feb.25th No Work Day
26-Feb*
Deep Learning in Medicine
Zhang 2020
1-Mar
TBD
3-Mar
Reinforcement Learning
Mnih2013, Volodymyr2013
5-Mar*
Reinforcement Learning
course proj. part3 out
8-Mar
Generative Adversarial Networks
Goodfellow2014
course proj.part2. due
10-Mar
Generative Adversarial Networks
course proj. proposal
12-Mar*
Technical Writing | Discussion Course Proj.
15-Mar
Technical Writing | Discussion Course Proj.
17-Mar
TBD
19-Mar*
Image Synthesis
Portenier 2019
22-Mar
Image Denoising
Bako2017
24-Mar
March 24th Recharge Day: No Class
written hw out
26-Mar*
Motion from Video
Karpathy 2014, Vondrick2016
29-Mar
Motion from Video
31-Mar
Learning from Physics
Lerer2016
course proj.mid eval
2-Apr*
Learning from Physics
written hw due
5-Apr
Take Home Exam
Take Home Exam Due: April 7, 11:59pm
7-Apr
Autonomous Driving
TED Talk 1.
9-Apr
Autonomous Driving
Janai 2017
12-Apr
Autonomous Driving
14-Apr
TBD
16-Apr
TBD
19-Apr
Robotics
TED Talk 2.
21-Apr
Robotics
Pinto 2017
course proj.part3. due

 

***weekly in class quiz dates

COURSEWORK

All assignments are distributed and submitted in Canvas.

60% Course Project (submitted in three parts)

15%  Take Home Exam (1)

15%  Written Homework (1)

10%  Quizzes (~weekly)

 

Attendance Policy, Class Expectations, and Make-Up Policy
Attendance is expected and noted. One half of a letter grade will be deducted (e.g. an A becomes a B+) for missing more than 3 classes for the semester without a documented university excused absence. Make-Up homework, projects and exams will be coordinated with the instructor for university excused absences. Excused absences must be consistent with university policies in the graduate catalog (http://gradcatalog.ufl.edu/content.php?catoid=10&navoid=2020#attendance) and require appropriate documentation.

 

Grading Policy
93.4 – 100 A 4.00
90.0 – 93.3 A- 3.67
86.7 – 89.9 B+ 3.33
83.4 – 86.6 B 3.00
80.0 – 83.3 B- 2.67
76.7 – 79.9 C+ 2.33
73.4 – 76.6 C 2.00
70.0 – 73.3 C- 1.67
66.7 – 69.9 D+ 1.33
63.4 – 66.6 D 1.00
60.0 – 63.3 D- 0.67
0 – 59.9 E 0.00

More information on UF grading policy may be found at:
http://gradcatalog.ufl.edu/content.php?catoid=10&navoid=2020#grades

Late Policy: Late programming projects will receive a late penalty of 10% per day late up to a maximum of a 50% reduction unless there is a documented university excused absence. Students are permitted 1 free late pass for 1 programming assignment (not including the final project which is due at the end of the semester). No late penalties will be applied for up to 1 week over the deadline when using a late pass. The written homework is reviewed in class in preparation for the exam and cannot be turned in late without a documented university excused absence.

 

Students Requiring Accommodations
Students with disabilities who experience learning barriers and would like to request academic accommodations
should connect with the disability Resource Center by visiting https://disability.ufl.edu/students/get-started/. It is
important for students to share their accommodation letter with their instructor and discuss their access needs, as
early as possible in the semester.
Course Evaluation
Students are expected to provide professional and respectful feedback on the quality of instruction in this course by
completing course evaluations online via GatorEvals. Guidance on how to give feedback in a professional and
respectful manner is available at https://gatorevals.aa.ufl.edu/students/. Students will be notified when the
evaluation period opens, and can complete evaluations through the email they receive from GatorEvals, in their
Canvas course menu under GatorEvals, or via https://ufl.bluera.com/ufl/. Summaries of course evaluation results
are available to students at https://gatorevals.aa.ufl.edu/public-results/.

 

In-Class Recording
Students are allowed to record video or audio of class lectures. However, the purposes for which these recordings
may be used are strictly controlled. The only allowable purposes are (1) for personal educational use, (2) in
connection with a complaint to the university, or (3) as evidence in, or in preparation for, a criminal or civil
proceeding. All other purposes are prohibited. Specifically, students may not publish recorded lectures without the
written consent of the instructor.

 

A “class lecture” is an educational presentation intended to inform or teach enrolled students about a particular
subject, including any instructor-led discussions that form part of the presentation, and delivered by any instructor
hired or appointed by the University, or by a guest instructor, as part of a University of Florida course. A class
lecture does not include lab sessions, student presentations, clinical presentations such as patient history,
academic exercises involving solely student participation, assessments (quizzes, tests, exams), field trips, private
conversations between students in the class or between a student and the faculty or lecturer during a class session.
Publication without permission of the instructor is prohibited. To “publish” means to share, transmit, circulate,
distribute, or provide access to a recording, regardless of format or medium, to another person (or persons),
including but not limited to another student within the same class section. Additionally, a recording, or transcript
of a recording, is considered published if it is posted on or uploaded to, in whole or in part, any media platform,
including but not limited to social media, book, magazine, newspaper, leaflet, or third party note/tutoring services.
A student who publishes a recording without written consent may be subject to a civil cause of action instituted by
a person injured by the publication and/or discipline under UF Regulation 4.040 Student Honor Code and Student
Conduct Code.
University Honesty Policy
UF students are bound by The Honor Pledge which states, “We, the members of the University of Florida community,
pledge to hold ourselves and our peers to the highest standards of honor and integrity by abiding by the Honor Code.
On all work submitted for credit by students at the University of Florida, the following pledge is either required or
implied: “On my honor, I have neither given nor received unauthorized aid in doing this assignment.” The Conduct
Code (https://sccr.dso.ufl.edu/process/student-conduct-code/) specifies a number of behaviors that are in violation
of this code and the possible sanctions. If you have any questions or concerns, please consult with the instructor or
TAs in this class.

 

Commitment to a Safe and Inclusive Learning Environment

The Herbert Wertheim College of Engineering values broad diversity within our community and is committed to
individual and group empowerment, inclusion, and the elimination of discrimination. It is expected that every
person in this class will treat one another with dignity and respect regardless of gender, sexuality, disability, age,
socioeconomic status, ethnicity, race, and culture.
If you feel like your performance in class is being impacted by discrimination or harassment of any kind, please
contact your instructor or any of the following:
• Your academic advisor or Graduate Program Coordinator
• Jennifer Nappo, Director of Human Resources, 352-392-0904, jpennacc@ufl.edu
• Curtis Taylor, Associate Dean of Student Affairs, 352-392-2177, taylor@eng.ufl.edu
• Toshikazu Nishida, Associate Dean of Academic Affairs, 352-392-0943, nishida@eng.ufl.edu
Software Use
All faculty, staff, and students of the University are required and expected to obey the laws and legal agreements
governing software use. Failure to do so can lead to monetary damages and/or criminal penalties for the individual
violator. Because such violations are also against University policies and rules, disciplinary action will be taken as
appropriate. We, the members of the University of Florida community, pledge to uphold ourselves and our peers to
the highest standards of honesty and integrity.
Student Privacy
There are federal laws protecting your privacy with regards to grades earned in courses and on individual
assignments. For more information, please see: https://registrar.ufl.edu/ferpa.html
Campus Resources:
Students will have access to a GPU cluster for completing the course project.

Campus Resources:
Students will have access to the HiPerGator GPU cluster for completing the course project.
Health and Wellness
U Matter, We Care:
Your well-being is important to the University of Florida. The U Matter, We Care initiative is committed to
creating a culture of care on our campus by encouraging members of our community to look out for one another
and to reach out for help if a member of our community is in need. If you or a friend is in distress, please contact
umatter@ufl.edu so that the U Matter, We Care Team can reach out to the student in distress. A nighttime and
weekend crisis counselor is available by phone at 352-392-1575. The U Matter, We Care Team can help connect
students to the many other helping resources available including, but not limited to, Victim Advocates, Housing
staff, and the Counseling and Wellness Center. Please remember that asking for help is a sign of strength. In case
of emergency, call 9-1-1.
Counseling and Wellness Center: https://counseling.ufl.edu, and 392-1575; and the University Police
Department: 392-1111 or 9-1-1 for emergencies.
Sexual Discrimination, Harassment, Assault, or Violence
If you or a friend has been subjected to sexual discrimination, sexual harassment, sexual assault, or violence
contact the Office of Title IX Compliance, located at Yon Hall Room 427, 1908 Stadium Road, (352) 273-1094,
title-ix@ufl.edu
Sexual Assault Recovery Services (SARS)
Student Health Care Center, 392-1161.
University Police Department at 392-1111 (or 9-1-1 for emergencies), or http://www.police.ufl.edu/.
COVID-19
• You are expected to wear approved face coverings at all times during class and within buildings even if
you are vaccinated.
• If you are sick, stay home and self-quarantine. Please visit the UF Health Screen, Test & Protect website
about next steps, retake the questionnaire and schedule your test for no sooner than 24 hours after your
symptoms began. Please call your primary care provider if you are ill and need immediate care or the UF
Student Health Care Center at 352-392-1161 (or email covid@shcc.ufl.edu) to be evaluated for testing and
to receive further instructions about returning to campus.
• If you are withheld from campus by the Department of Health through Screen, Test & Protect, you are not
permitted to use any on campus facilities. Students attempting to attend campus activities when withheld
from campus will be referred to the Dean of Students Office.
• UF Health Screen, Test & Protect offers guidance when you are sick, have been exposed to someone who
has tested positive or have tested positive yourself. Visit the UF Health Screen, Test & Protect website for
more information.
• Please continue to follow healthy habits, including best practices like frequent hand washing. Following
these practices is our responsibility as Gators.
Academic Resources
E-learning technical support, 352-392-4357 (select option 2) or e-mail to Learning-support@ufl.edu.
https://lss.at.ufl.edu/help.shtml.
Career Resource Center, Reitz Union, 392-1601. Career assistance and counseling; https://career.ufl.edu.
Library Support, http://cms.uflib.ufl.edu/ask. Various ways to receive assistance with respect to using the
libraries or finding resources.
Teaching Center, Broward Hall, 392-2010 or 392-6420. General study skills and tutoring.
https://teachingcenter.ufl.edu/.
Writing Studio, 302 Tigert Hall, 846-1138. Help brainstorming, formatting, and writing papers.
https://writing.ufl.edu/writing-studio/.
Student Complaints Campus: https://sccr.dso.ufl.edu/policies/student-honor-code-student-conductcode/;https://care.dso.ufl.edu.
On-Line Students Complaints: http://www.distance.ufl.edu/student-complaint-process.

Leave a Reply

Your email address will not be published.