Welcome   to   the   MLSP   page

Signal Processing is the science that deals with extraction of information from signals of various kinds. This 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.

A 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 techniques to process signals. We cover a variety of topics, from data driven approaches for characterization of signals such as audio including speech, images and video, and machine learning methods for a variety of speech and image processing problems.

Instructors

Professor: Bhiksha Raj
Office: GHC office 6705
Teaching Assistant (Pittsburgh): Mahmoud Al Ismail
Office Hours: Tuesday: 11AM-12PM (EDT) GHC 5417, Wednesday: 2PM-3PM (EDT) GHC 6708

Teaching Assistant (Pittsburgh): Xinya Li
Office Hours: Monday: 3PM - 4PM (EDT) GHC 5417, Thursday: 2PM-3PM (EDT) GHC 5417

Teaching Assistant (Silicon Valley): Yandong Wen
Office Hours: Tuesday: 4:30PM-5:30PM (EDT) Online (find link on Piazza)

Teaching Assistant (Kigali): Samuel Ishimwe
Office: Telecom House, 1st floor, TAs office
Office Hours: Wednesdays: 6PM-7PM (GMT+2), Thursdays: 7PM-8PM (GMT+2)

Grading

Weekly quizzes (25%), homeworks (50%), project(25%)

Prerequisites

Mandatory: Linear Algebra, Basic Probability Theory.

Recommended: Signal Processing, Machine Learning

Class   Timings

Tuesdays and Thursdays, 3:00-4:20pm at Baker Hall BH 136A.

Related   Webpages