This course comprehensively explores how advanced deep learning techniques can be applied to solve various challenges in electronic engineering. It examines the use of neural networks for core tasks like signal detection, recognition, analysis, prediction, synthesis, and generation. It explores how deep learning can enhance the understanding, manipulation, and even the creation of electronic signals and data, providing students with a robust foundation in this rapidly evolving intersection of artificial intelligence and electronic engineering.

The course begins by characterising electronic signals and systems across various dimensions and outlines core engineering tasks related to signal and sensor data. It then introduces machine learning principles that form the basis of deep learning and continues with the following topics: discriminative deep learning models for both multi-dimensional signal analysis and sequential data processing, generative deep learning methods for signal enhancement and synthesis, emerging applications of deep learning in electronic systems, including the integration of physical principles through Physics-Informed Neural Networks, concluding with a forward-looking perspective on the field's future directions.