CS 795: Deep Learning (Syllabus)

Class Information
Class/Sec: CS 795 (002): Deep Learning
Instructor: Huzefa Rangwala Room #4423 Engineering Building, rangwala@cs.gmu.edu
Class Time & Location: Wed 4:30 - 7:10 pm Innovation Hall 136
Text Book: (Recommended) Deep Learning by Goodfellow et. al. Here (Reference) Neural Networks and Deep Learning by Aggarwal Here Lots of papers: Close to 4/week on an average
Office Hours: Instructor: Wed 2:30-3:30 pm in Engineering 4423.
Communication and Class Link: Piazza Link: Piazza

Please note the syllabus is subject to change to enrich the student's learning experience :). Feel free to email rangwala@cs.gmu.edu for questions, concerns, or even say hi.

About the Course
Course Description
Deep learning are a class of machine learning algorithms that seek to learn data representations. Algorithms inspired by the structure and function of brains, deep learning algorithms find them applied in several application domains. In this class we gain a quick introduction in the history and basics of these algorithms and then seek to advance deep learning research in terms of theory and applications.
Course Prerequisites
CS 688. Strong programming experience in language of your choice. Linear Algebra and Calculus. Willingness to learn, discuss and present. Expreience in reading technical research papers.
Course Format
This is a specials topic seminar class. A combination of instructor leading discussions (not presenting), group discussions and student presentations will be used for covering topics associated with this class. Besides material from the textbook, topics not discussed in the book may also be covered. Homework assignments and final project will require a substantial programming effort. Exams and homework assignments must be done on an individual basis unless stated. Any deviation from this policy will be considered a violation of the GMU Honor Code
Course Outcomes
As an outcome of taking this class, a student will be able to
  • Understand the theory underlying deep learning algorithms.
  • Apply deep learning approaches to real world scientific and/or industrial applications.
  • Read about cutting-edge research papers in the field and be poised to make their own technical contributions.

Topics

See page for detailed listing of topics

Assignments/Exams
Deliverables Grade Weights
Four Paper Reading Summary, Critiques 10%
Class Discussions 10%
Two Paper Presentations 15%
Two Homeworks (Involve Programming) 20%
Project Pitch 0%
Project Proposal 5%
Video and Final Presentation 10%
Project Report 30%
Grade Distribution
Grade Score Range
A >96
A- 92-96
B+ 88-92
B 84-88
B- 80-84
C+ 76-80
C 72-76
C- 68-72
F < 68
Policies:
Attendance
Attendance is not compulsory but highly recommended for doing well in the class. The class has weekly discussion and points based on that. This class has lots of active learning exercises, and they will be a lot of fun.
Assignment Submission
Please ensure that the assignments are submitted on-time. No late submissions are allowed.
Make-Up Exams & Incompletes
Make up exams and incompletes will not be given for this class.
Academic Honesty and GMU Honor Code
Please visit the GMU Honor Code and do not copy assignment solutions from your peers, internet or any source unless stated in the assignment description.
Disability Statement
If you have a documented learning disability or other condition that may affect academic performance you should: 1) make sure this documentation is on file with the Office of Disability Services (SUB I, Rm. 222; 993-2474; www.gmu.edu/student/drc to determine the accommodations you need; and 2) talk with me to discuss your accommodation needs.