IST 597:  Foundations of Deep Learning
  Fall 2019

Instructor: Dr. C. Lee Giles

TAs: Ankur Mali
Kaixuan Zhang

Time and Place:  2:30-5:30, Wednesday, 121 Earth and Engineering Sciences.

Office Hours:  Giles, Thursday 3-4,  E350 Westgate Bldg.
                         Ankur Mali, Tuesday 2:30-4, Thursday 10:30-12, E345 Westgate Bldg.
                         Kaixuan Zhang, Monday 2:30-4, Thursday 4-5:30, E301 Westgate Bldg.

Course Overview

This is a three hour course hands on course for graduate students that meets once a week. The course will introduce the mathematical foundations of deep learning: linear algebra, numerical computation, and machine learning basics. We will then cover modern practical deep networks and their applications. We will investigate deep feedforward networks, convolutional networks, and recurrent networks as well as practical methodologies, including model regularization and parameter optimization. Practical applications will be utilized for course projects.

Course Mission Statement:

This course is intended to prepare students to understand, design, develop and use deep learning methods.

Course Prerequisites:

Students should be able to learn the basics of deep learning fundamentals.

Schedule (syllabus):
  This schedule is subject to change. Please check it on a regular basis for assignments. The reading list is also there; most classes will have online handouts such as powerpoint or PDF. It is the student's responsibility to download that material.

Course Materials and References:
Course materials can be found here. There will also be links on the schedule.

        Research Project: 50%
                            Project proposal and presentation: 10%
                            Final project presentation and paper: 40%
                       Exercises: 40%

                       Paper review presentations: 10%

                       Student information form: this must be filled out and turned in order to receive a grade.


There will be 5 exercises, each counting 8 points, all in TensorFlow.

All exercises are due by midnight of the due date and must be submitted as a zip or gzip which includes PDF and PythonScript[.py].
Late exercises will receive 50% credit for the first 24 hours and no credit after that time.

Texts and Readings: 

The reading list is on the schedule above.  We will use chapters and sections from the online text:

Research Project:

Students will be placed in teams.

Each team will propose and investigate an interesting project on deep learning. Machine learning competitions are possible projects as are applications, comparisons and original research.  For suggestions, please see the instructor or the TA.

There will be a proposed topic presentation, a final presentation, and a project paper in PDF and hard copy in the ACM paper format.


There will be two presentations for the project and two for assigned research papers to review.
For the assigned papers, each team will make a review presentation on their two assigned paper(s).

Email: All email to the instructor and TA about this class should contain "IST597" in the subject line.  For example, the subject line might read "IST597: Question about ....".  Email without this information might be deleted by spam filters or placed in a folder to be read at a later date.  Email with the appropriate identifier will usually be read within 24 hours of being received.


Reuse: Materials from this course can be publicly reused in other courses. This course supports Open Educational Resources (OER).