While there are no strict formal prerequisites for some versions of the course, a strong technical background is essential for success.

Using a simulated uniform linear array (ULA) of antennas, students receive signals from two narrowband sources at different angles. The task:

The structure of ELEC5307 is meticulously designed to build from classical estimation theory to contemporary data-driven methods. Typically, the course is divided into four major modules.

One of the most rewarding (and challenging) aspects was the hands-on project work. For instance, in our recent work on image categorization, success wasn't just about hitting "run." It required meticulous dataset management—splitting 50,000 images into precise training and validation sets—and constantly monitoring loss curves to prevent overfitting. Why This Matters