ECE 5630 - Information Theory for Data Transmission, Security, and Machine Learning

ECE 5630 - Information Theory for Data Transmission, Security, and Machine Learning

For whom?

The course is inteded for graduate students interested in mathematical foundations of information theory and their applications to the study of data transmission, secure communication and machine learning. Knowledge of probability theory and mathematical maturity are prerequisite.

 

Time and Location:

Lectures: TuTh255-410, 206 Upson Hall

Office Hours: We9-11, 322 Rhodes Hall

Instructor: Ziv Goldfeld, 322 Rhodes Hall

 

News:

 

Homework Sheets:

 

Lecture notes:

 

Overview:

Information theory studies the quantification, compression, communication and encryption of information. Through elegant mathematical formulations of operational problems coupled with powerful techniques, information theory characterizes fundamental performance limits and provides deep engineering insight into the design of the underlying systems. The course We will cover both classical and modern topics, starting from f-divergences, information measures and relations between them. Using these tools we will explore optimal data transmission (rates) over noisy channels. We will then cover distribution simulation and leverage it to study information-theoretically secure communication in the presence of a (passive or active) eavesdropper. Finally, we will explore connections between information theory and machine learning, examining how these fields can cross-fertilize each other.

 

Format:

Two 1:15hr lectures per week, with a midterm and a final exam.

 

Tentative List of Topics: