Machine Learning for Signal Processing

Signal processing is the science of extracting information from signals of every kind, and it has two distinct aspects: characterization and categorization. Traditionally, signal characterization has been performed with mathematically-driven transforms, while categorization and classification are achieved using statistical tools. Machine learning aims to design algorithms that learn about the state of the world directly from data. An increasingly popular trend has been to develop and apply machine learning techniques to both aspects of signal processing, often blurring the distinction between the two. This course discusses the use of machine learning to process signals — from data-driven approaches for characterizing audio, speech, images and video, to machine learning methods for a variety of speech and image processing problems.