This course covers machine learning basics, supervised/unsupervised learning, classification/regression, cost functions, stochastic gradient descent, and backpropagation for wireless communications. This course enables students to apply machine learning techniques to wireless communication tasks like signal detection, decoding, compression, and resource allocation.
Python, MATLAB
Upon successful completion of this course, students will be able to:
(1) List different types of machine learning problems, including supervised/unsupervised learning, classification, and regression problems,
(2) Describe the fundamental principles of the training process, including stochastic gradient descent and the backpropagation algorithm,
(3) Discover the characteristics and applications of different classes of neural networks, including convolutional neural networks and autoencoders,
(4) Differentiate between reinforcement learning techniques and previously studied learning techniques,
(5) Analyze the performance of machine learning-aided components employed in wireless communication systems,
(6) Generate practical activities and projects to grasp machine learning's potential in enhancing wireless communication.
(1) Eldar, Y. C., Goldsmith, A., Gunduz D., & Poor, H. V. (2022). Machine Learning in Wireless Communications. Cambridge University Press.
(2) Goodfellow, I., Bengio, Y., & Courville A. (2016). Deep Learning. MIT Press.
Test/Exam (50%), Performance Project (Written, Oral) (30%), Quiz (10%), Case Studies / Homework (10%)
| Workload | Hrs |
|---|---|
| Lectures | 42 |
| Course Readings | 60 |
| Exams/Quizzes | 60 |
| Report on a Topic | 42 |
| Case Study Analysis | 21 |