CS 498 DV – Machine Learning in Wireless Systems

Instructor: Deepak Vasisht(deepakv@illinois.edu)

Lectures: Tuesday, Thursday – 2:00 pm to 3:15 pm Central Time

Venue: 1DCL-1310

Office Hours: Tuesday, 3:30 pm to 4:30 pm (Siebel Center 3110)

TA: Jay Shenoy (jshenoy2@illinois.edu) OH: Wednesday, 4:00 pm to 5:00 pm (Siebel Center 3105)


Wireless Networks like 5G, Wi-Fi, and LoRa form a backbone for modern computing systems including Internet of Things, smartphones, audio-visual communication, etc. Modern wireless networks are increasingly being transformed by Machine Learning approaches. This course will focus on this intersection of machine learning with wireless networks. Specifically, this course will discuss some primitives of wireless networks (communication, sensing, positioning) and how these primitives are being transformed by modern Machine Learning technologies. Students will also learn about applications of wireless networks in different domains like robotics, agriculture, satellites, and healthcare. The course assumes some basic knowledge of linear algebra and Machine Learning, so a prior course in either of these domains is preferred for students taking this class.


This class will cover the following topics:

  • Wireless Communications

  • Wireless Sensing

  • Positioning using radio signals

  • Machine Learning: Regression

  • Machine Learning: Neural Networks

  • Machine Learning for Internet of Things

  • Applications of ML in wireless communications

  • Applications of ML in wireless sensing and positioning

  • Machine Learning in next generation systems (6G, satellite networking)

About the Course


Knowledge and comfort with linear algebra, matrices, and complex numbers will help you in this class. If you have taken a class in machine learning or wireless networks or embedded systems, the class material will be easier to access. If you are not sure about the prerequisites, email Deepak or Jay.


The class will be graded as follows:

  • Reading Assignments: 10%

  • 2 Problem Sets: 25% (12.5 each)

  • Class Participation: 10%

  • Midterm: 25%

  • Class Project: 30%

If you are doing a 3-credit version of the class, the expectation will be lower on the class project and you can skip one problem set.

Reading Assignments

Each class will have one reading assignments which we will read prior to the class. To get the most out of the class, the students should read the papers in detail before the class. Before each class, the students should submit answers to two-three questions about the readings posted on the course website. The answers are due at 11:59 pm on the night prior to the class. You are allowed five free skips. An answer submitted after the deadline but before the class counts as half-skip.

Problem Sets

We will have two problem sets with a mix of theoretical and implementation problems. For the implementation part, you can write the code either in Python or Matlab. You will need to submit the code prior to the deadlines.

Class Participation

We expect you to attend every class. Please contact Deepak if you cannot make it to some classes. Class participation grade is dependent on your participation in class discussions.


Details will be released closer to the midterm.

Class Project

We plan to give students two options for their class projects.

Research Project: You can pursue a research direction of your choice. The instructor will help you identify problems in your domain of interest and guide your initial research. The research projects should aim really high – the best research projects will lead to interesting demos or even research papers in top conferences like SIGCOMM, NSDI, MobiCom, SenSys, etc. If your project is too ambitious to be executed in a semester, we will help you to find a smaller chunk that you can execute in class duration. If you are taking the 4-credit version of the class, you should plan on doing a research project.

Competition: We will setup an intra-class competition for running Machine Learning on a practical wireless problem (such as spectrum sensing, localization, satellite networking).

Teams: Students can form teams of 2 to work on class projects. Teams of 3 are also OK, but the expectation on contribution is higher.

Anti-racism and Inclusivity

The intent of this section is to raise student and instructor awareness of the ongoing threat of bias and racism and of the need to take personal responsibility in creating an inclusive learning environment.

The Grainger College of Engineering is committed to the creation of an anti-racist, inclusive community that welcomes diversity along a number of dimensions, including, but not limited to, race, ethnicity and national origins, gender and gender identity, sexuality, disability status, class, age, or religious beliefs. The College recognizes that we are learning together in the midst of the Black Lives Matter movement, that Black, Hispanic, and Indigenous voices and contributions have largely either been excluded from, or not recognized in, science and engineering, and that both overt racism and micro-aggressions threaten the well-being of our students and our university community.

The effectiveness of this course is dependent upon each of us to create a safe and encouraging learning environment that allows for the open exchange of ideas while also ensuring equitable opportunities and respect for all of us. Everyone is expected to help establish and maintain an environment where students, staff, and faculty can contribute without fear of personal ridicule, or intolerant or offensive language. If you witness or experience racism, discrimination, micro-aggressions, or other offensive behavior, you are encouraged to bring this to the attention of the course director if you feel comfortable. You can also report these behaviors to the Bias Assessment and Response Team (BART) (https://bart.illinois.edu/). Based on your report, BART members will follow up and reach out to students to make sure they have the support they need to be healthy and safe. If the reported behavior also violates university policy, staff in the Office for Student Conflict Resolution may respond as well and will take appropriate action.