IST 597: Foundations of Deep Learning
and Place: Fall, 2018. 2:30-5:30, Wednesday, 121 Earth and
Hours: Giles, Thursday 3-4, E350 Westgate Bldg.
Tuesday 1:30-3:30, E345 Westgate Bldg.
This is a three hour course for graduate students that meets once a
week. The course will introduce the mathematical foundations of deep
learning: linear algebra, probability and information theory,
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.
This course is intended to prepare students to understand, design,
develop and use deep learning methods.
Students should be able to learn the basics of deep learning
(syllabus): This schedule is
subject to change. Please check it on a regular basis for
assignments. The reading list is here; most classes will have online
handouts. It is the student's responsibility to download that
Materials and References: Course materials can
be found here. There will also be links on the schedule.
Project proposal: 10%
Final project and presentation: 50%
There will be two exercises.
Texts and Readings:
The reading list is on the schedule above. We will use
chapters and sections from the online text:
- Deep Learning,
Ian Goodfellow, Yoshua Bengio, Aaron Courville, MIT Press,
- Papers where appropriate.
- For TensorFlow, there are many books and online
tutorials. These books are recommended:
Students will be placed in teams. Each team will propose and
investigate an interesting application of deep learning.
There will be a proposed topic presentation, a final presentation,
and a research paper in ACM
There will be two presentations for the project and two for assigned
research papers to review.
For the assigned papers, each team will make two review
presentations on the 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.