EE269 - Signal Processing for Machine LearningAnnouncements
Course descriptionThis course will introduce you to fundamental signal processing concepts and tools needed to apply machine learning to discrete signals. You will learn about commonly used techniques for capturing, processing, manipulating, learning and classifying signals. The topics include: mathematical models for discrete-time signals, vector spaces, Hilbert spaces, Fourier analysis, time-frequency analysis, filters, signal classification and prediction, basic image processing, adaptive filters and neural nets. With time, we will cover advanced topics including wavelets, deep learning and compressed sensing. This class will culminate in a final project. Prerequisites:Exposure to signals and systems (EE 102A and EE 102B or equivalent), basic probability (EE 178 or equivalent), basic programming skills (Matlab), familiarity with linear algebra (EE 103 and EE 178 are recommended). Instructor: Mert Pilanci, pilanci@stanford.edu |