Machine learning has achieved huge success in many engineering applications such as computer vision, gene discovery, financial forecasting, credit card fraud detection, autonomous vehicle navigation, biomedical signal modeling, wireless/radar/aerospace systems and others. The course will briefly review discrete-time signals and systems, including convolution and Fourier transforms. This course will introduce the fundamental concepts, algorithms, and theories in machine learning, including linear models, projection/nonlinear embedding methods, neural networks/deep learning, parametric/non-parametric methods, kernel machines, mixture models, and pattern recognition/classification. Also, the lectures will briefly summarize recent trends in the field to provide students with cutting-edge knowledge for engineering. The course will give the student the basic ideas and intuition behind these methods, as well as a more formal understanding of how and why they work. Students will have an opportunity to experiment with machine learning techniques and apply them in one or more application-based projects.
ECE 2312, Discrete-Time Signal and System Analysis; ECE 2039 Computational Engineering (pending course approval). Students who have taken ECE 340X may not get credit for ECE 3405.