Tarek Abdelzaher,
Office Hours: Mondays, 11am-noon

Lecture Times

Tuesdays and Thursdays, 12:30 – 1:45pm (SC 0216)


An expanding frontier for computer scientists lies at the intersection of the logical and physical realms. As intelligent computing elements become embedded more pervasively in our environment, a new cyber-physical fabric arises in which logical processing is deeply intertwined with the physical environment in which it occurs. The course explores the science of designing and analyzing systems that are guaranteed to perform their functions in a timely manner, with an emphasis on challenges in accommodating machine intelligence at the edge (Edge AI). A real-time AI simulation testbed is used to illustrate some of the concepts. Selected topics include:

  • - Review of basic concepts (tasks, threads, blocking, priorities, importance, resource partitioning, etc.)
  • - The Reliability Dimension: Complexity reduction, well-formed dependencies, and fail-safe operation
  • - The Time Dimension: Real-time scheduling and timeliness guarantees
  • - The Resource Dimension: Compression, edge AI, power-aware algorithms, and energy saving issues
  • - Real-time AI
  • - Other Challenges

The course will involve 5 homeworks, 2 programming assignments, two midterms, and a final that encourage you to analyze and evaluate concepts covered under the above topics. Grades will be assigned as follows:

  • - Homework: Homework grades will collectively account for 20% of the total grade. You must work on homework by yourself.
  • - Programming assignments: Programming assignments will collectively account for 20% of the total grade. They are done in groups of 3-4 students.
  • - Midterm 1: An open-book midterm exam will be held for 15% of the grade.
  • - Midterm 2: An open-book midterm exam will be held for 15% of the grade.
  • - Final: A final exam with be held for 20% of the grade.
  • - Class Participation: Accounts for 10%. Includes attendance and class discussion.

Why are Real-time and Cyber-physical Systems Important?

This technology is also not in a vacuum. More sensors will lead to more data, which will lead to more analysis and more advancements with AI and machine learning. Everything is connected, figuratively and literally.

The need for [real-time edge analytics] is being driven by the mass of information being collected at the edge. The real expense is going to be shipping all that data back to the cloud to be processed when it doesn't need to be.

The Internet will disappear. There will be so many IP addresses, so many devices, sensors, things that you are wearing, things that you are interacting with, that you won't even sense it. It will be part of your presence all the time.