ECE 59500: Introduction to Deep Learning

Lecture Hours: 3 

Credits: 3

Area of Specialization: Communications, Networking, and Signal & Image Processing (CNSIP)

Catalog Description:
This course provides focused training on deep learning algorithms. The students should be able to acquire a principled understanding for the various techniques that have a proven successful record in solving important engineering problems. Further, hands-on experimental training will be provided through the course projects.

Learning Outcomes:

  1. Make design choices regarding the construction of deep learning algorithms.
  2. Learn about the history and justification for state-of-the-art deep learning algorithms.
  3. Implement, optimize and tune state-of-the-art deep neural network architectures.
  4. Learn about the security aspects of state-of-the-art deep learning algorithms.
  5. Learn about open research problems in deep learning and proposed approaches in the literature to tackle them.

Required Text(s): None; class notes are available at https://web.ics.purdue.edu/~elgamala/ECE595/notes.html

Recommended Reference: Deep Learning, 1st Edition, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT Press, 2016, ISBN No. 0262035618. Available at https://deeplearningbook.org