Public View

You are viewing the public version of the syllabus. If you have a SUNet account, you can view the richer version of the syllabus after logging in.

Machine Learning for Communication Systems
EE 58009

Faculty: Faculty of Engineering and Natural Sciences
Semester: Fall 2025-2026
Course: Machine Learning for Communication Systems - EE 58009
Classroom: FENS-L065,FENS-L067
Level of course: Masters
Course Credits: SU Credit:3.000, ECTS:10
Prerequisites: -
Corequisites: -
Course Type: Lecture

Instructor(s) Information

Çağlar Tunç

Course Information

Catalog Course Description
This course introduces students to the application of machine learning techniques in modern communication systems. Topics include supervised and unsupervised learning, neural networks, reinforcement learning, and explainable AI, with a focus on problems such as traffic classification, channel estimation, resource management, and anomaly detection. Students will also explore ML-based network layer optimizations in wireless systems, including 5G/6G. Hands-on assignments and projects using real-world communication datasets and open-source simulation tools will reinforce the concepts.
Course Learning Outcomes:
1. Understand and explain key machine learning concepts and how they apply to communication systems.
2. Implement ML algorithms to solve problems such as channel estimation, signal classification, and resource allocation.
3. Evaluate the performance and limitations of ML-based solutions in communication scenarios.
4. Apply explainable and interpretable AI techniques to build trustworthy models for communication system tasks.
5. Use simulation tools and real datasets to analyze and prototype intelligent communication systems.
Course Objective
-

Course Materials

Resources:
Any versions of the following books:
Applications of Machine Learning in Wireless Communications, by Ruisi He; Ruisi Zhiguo Ding
Machine Learning and Wireless Communications, by Yonina C. Eldar, Andrea Goldsmith, Deniz Gündüz, H. Vincent Poor
Wireless Communications, by Andreas F. Molisch
Technology Requirements: