T81-558: Applications of Deep Neural Networks

Washington University in St. Louis

Fall 2018, Mondays, 6 - 8:30 PM, Online and TBA

Jeff Heaton, Ph.D., [email protected]

http://sites.wustl.edu/jeffheaton
(636) 525-1842

This syllabus is subject to change as the semester progresses.

Course Description: Deep learning is a group of exciting new technologies for neural networks.
Through a combination of advanced training techniques and neural network architectural com-
ponents, it is now possible to create neural networks of much greater complexity. Deep learning
allows a neural network to learn hierarchies of information in a way that is like the function of the
human brain. This course will introduce the student to computer vision with Convolution Neu-
ral Networks (CNN), time series analysis with Long Short-Term Memory (LSTM), classic neural
network structures and application to computer security. High Performance Computing (HPC)
aspects will demonstrate how deep learning can be leveraged both on graphical processing units
(GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems,
with some introduction mathematical foundations. Students will use the Python programming lan-
guage to implement deep learning using Google TensorFlow and Keras. It is not necessary to know
Python prior to this course; however, familiarity of at least one programming language is assumed.
This course will be delivered in a hybrid format that includes both classroom and online instruction.

Prerequisite(s): None; however, general programming experience is assumed. The Python pro-
gramming language will be used for this class and reviewed as appropriate. Elements from mathe-
matics (generally at a Calculus I level) will be introduced and explained.

Credit Hours: 3

Text: No required text.

Course Objectives:
At the completion of this course, students will be able to:

1. Explain how neural networks (deep and otherwise) compare to other machine learning models.
2. Determine when a deep neural network would be a good choice for a particular problem.
3. Demonstrate their understanding of the material through a final project.

1
Grade Distribution:
Programming Assignments (10) 25%
Kaggle Project 20%
Midterm (in class) 20%
Final Project 20%
Current Topics 15%

Letter Grade Distribution:

100 A+ 77 C+
94 A 75 C
87 A- 73 C-
85 B+ <73 F
82 B
79 B-
Course Policies:
• General

– No makeup quizzes or exams will be given.

– Grades in the C range represent performance that is below expectations; Grades in
the B range represent performance that meets expectations; Grades in the A range
represent work that is excellent.
– Grades will be maintained online. Students are responsible for tracking their progress
by referring to the the university’s Blackboard system.

• Programs and Assignments

– Students are expected to work independently. Offering and accepting solutions from
others is an act of plagiarism, which is a serious offense and all involved parties will
be penalized according to the Academic Honesty Policy. Discussion amongst
students is encouraged, but when in doubt, direct your questions to the professor, tutor,
or lab assistant.
– Programs that fail to compile will not receive a grade higher than 79%. Programs that
do not produce the correct output will not receive a grade higher than 89%. Original
programs that produce the expected output will always receive 100%. For multi-question
programming assignment, each question is evaluated individually.
– No late assignments will be accepted under any circumstances.

• Attendance and Absences

– This is a hybrid format class. Attendance of the 4 inclass sessions is very important.
Attendance is expected and will be taken each class. For each unexcused absence the
student will loose one percentage point of their grade (e.g. 95% to 94% for one missed
class).
– Students are responsible for all missed work, regardless of the reason for absence. It is
also the absentee’s responsibility to get all missing notes or materials.

2
Academic Honesty Policy Summary:

Introduction
In addition to skills and knowledge, COLLEGE/UNIVERSITY aims to teach students appropriate
Ethical and Professional Standards of Conduct. The Academic Honesty Policy exists to inform
students and Faculty of their obligations in upholding the highest standards of professional and
ethical integrity. All student work is subject to the Academic Honesty Policy. Professional and
Academic practice provides guidance about how to properly cite, reference, and attribute the in-
tellectual property of others. Any attempt to deceive a faculty member or to help another student
to do so will be considered a violation of this standard.

Instructor’s Intended Purpose

The student’s work must match the instructor’s intended purpose for an assignment. While the in-
structor will establish the intent of an assignment, each student must clarify outstanding questions
of that intent for a given assignment.

Unauthorized/Excessive Assistance
The student may not give or get any unauthorized or excessive assistance in the preparation of any
work.

Authorship
The student must clearly establish authorship of a work. Referenced work must be clearly docu-
mented, cited, and attributed, regardless of media or distribution. Even in the case of work licensed
as public domain or Copyleft, (See: http://creativecommons.org/) the student must provide attri-
bution of that work in order to uphold the standards of intent and authorship.

Declaration
Online submission of, or placing one’s name on an exam, assignment, or any course document is
a statement of academic honor that the student has not received or given inappropriate assistance
in completing it and that the student has complied with the Academic Honesty Policy in that work.

Consequences
An instructor may impose a sanction on the student that varies depending upon the instructor’s
evaluation of the nature and gravity of the offense. Possible sanctions include but are not limited
to, the following: (1) Require the student to redo the assignment; (2) Require the student to com-
plete another assignment; (3) Assign a grade of zero to the assignment; (4) Assign a final grade
of “F” for the course. A student may appeal these decisions according to the Academic Grievance
Procedure. (See the relevant section in the Student Handbook.) Multiple violations of this policy
will result in a referral to the Conduct Review Board for possible additional sanctions. The full
text of the Academic Honesty Policy is in the Student Handbook.

Accommodations Based Upon Sexual Assault

The University is committed to offering reasonable academic accommodations to students who are
victims of sexual assault. Students are eligible for accommodation regardless of whether they seek
criminal or disciplinary action. Depending on the specific nature of the allegation, such measures
may include but are not limited to: implementation of a no-contact order, course/classroom assign-
ment changes, and other academic support services and accommodations. If you need to request
such accommodations, please direct your request to Kim Webb (kim [email protected]), Director

3
of the Relationship and Sexual Violence Prevention Center. Ms. Webb is a confidential resource;
however, requests for accommodations will be shared with the appropriate University administra-
tion and faculty. The University will maintain as confidential any accommodations or protective
measures provided to an individual student so long as it does not impair the ability to provide such
measures.

If a student comes to me to discuss or disclose an instance of sexual assault, sex discrimination, sex-
ual harassment, dating violence, domestic violence or stalking, or if I otherwise observe or become
aware of such an allegation, I will keep the information as private as I can, but as a faculty member
of Washington University, I am required to immediately report it to my Department Chair or Dean
or directly to Ms. Jessica Kennedy, the University’s Title IX Director. If you would like to speak
with directly Ms. Kennedy directly, she can be reached at (314) 935-3118, [email protected],
or by visiting the Title IX office in Umrath Hall. Additionally, you can report incidents or com-
plaints to the Office of Student Conduct and Community Standards or by contacting WUPD at
(314) 935-5555 or your local law enforcement agency. See: Title IX

You can also speak confidentially and learn more about available resources at the Relationship and
Sexual Violence Prevention Center by calling (314) 935-8761 or visiting the 4th floor of Seigle Hall.
See: RSVP Center

Bias Reporting
The University has a process through which students, faculty, staff and community members who
have experienced or witnessed incidents of bias, prejudice or discrimination against a student can
report their experiences to the University?s Bias Report and Support System (BRSS) team. See:
http://brss.wustl.edu

Mental Health
Mental Health Services professional staff members work with students to resolve personal and in-
terpersonal difficulties, many of which can affect the academic experience. These include conflicts
with or worry about friends or family, concerns about eating or drinking patterns, and feelings of
anxiety and depression. See: shs.wustl.edu/MentalHealth

4
Course Outline:
The weekly coverage might change as it depends on the progress of the class (note: for this class,
weeks end Sunday evening the day before class). All assignments are due by midnight on the date
specified, except the Kaggle submitted project (which is in GMT, see below).

Module Date Content

Meet on: • Python Preliminaries
Module 1
08/27/2018 • We will meet on campus this week! (1st Meeting)
Week of • Python for Machine Learning
Module 2
09/03/2018 • Module 1 Assignment due 09/04/2018
Week of • TensorFlow and Keras for Neural Networks
Module 3
09/10/2018 • Module 2 Assignment due 09/11/2018
Week of • Training a Neural Network
Module 4
09/17/2018 • Module 3 Assignment due 09/18/2018

Meet on: • Classification and Regression

Module 5 • Module 4 Assignment due 10/02/2018
10/01/2018
• We will meet on campus this week! (2nd Meeting)
Week of • Backpropagation and Other Training Techniques
Module 6
10/08/2018 • Module 5 Assignment due 10/09/2018
Week of • Convolutional Neural Networks and Computer Vision
Module 7
10/15/2018 • Module 6 Assignment due 10/16/2018
• Kaggle and Advanced Data Sets
Meet on: • Module 7 Assignment due 10/23/2018
Module 8
10/22/2018 • Midterm exam is given on campus this week! (3rd Meet-
ing)
Week of • Regularization and Dropout
Module 9
10/29/2018 • Module 8 Assignment due 10/30/2018
Week of • Time Series and LSTM/GRU Networks
Module 10
11/05/2018 • Module 9 Assignment due 11/06/2018

Meet on: • Natural Language Processing

Module 11 • Module 10 Assignment due 11/13/2018
11/12/2018
• We will meet on campus this week! (4th Meeting)
Week of • Security and Deep Learning
Module 12
11/19/2018 • Kaggle Assignment due 11/20/2018 (5PM, due to Kaggle)
Week of
Module 13 • Advanced/New Deep Learning Topics
11/26/2018
Week of • GPU, HPC and Cloud
Module 14
12/03/2018 • Final Project due 12/04/2018