Syllabus
Time and Place:
5:00-7:20pm Tuesdays, HNB 107
Course Description:
This seminar-style course will introduce participants to the state-of-the-art techniques in neural networks and statistical learning, for instance, as presented at top-level conferences like Neural Information Processing Systems (NIPS). The course readings will consist of seminal papers and very new (partially not even yet published) textbooks. Topics that will be discussed include maximum-likelihood estimation using the EM-algorithm, Bayesian neural networks, Gaussian approximation in Bayesian neural networks, variational methods, Markov Chain Monte Carlo methods, Gaussian Processes, Hidden Markov Models, Support Vector Machines for Classification, Support Vector Machines for Regression, Probabilitistic interpretation of Support Vector Machines, Learning and Generalization in a Function Analtyic Framework, nonparametric methods for classification and regression.
Skills from this course will be beneficial for applied and basic research in artificial intelligence (e.g., pattern recognition and classification, data mining, data visualiztion, robotics, machine learning, process control), computational neuroscience (e.g., motor control, functional brain modeling) and cognitive sciences (e.g., perception, memory, reasoning).
Class Format:
The course consists will be in a seminar style, emphasizing group discussions of the presented topics, with occasional lectures for introductory purpopses. Partipants are expected to give presenations on selected materials of the course, and to carry out small-projects involving implementations (e.g., matlab, C, C++, or any programming language of your choice) of the presented algorithms. There are no exams.
Grading:
- 25% active participation in class
- 75% "paper presentations" and/or "projects" and/or "solving statistical data problems"
Prerequisites:
Basic knowledge in linear algebra, calculus, statistics, neural networks, and programming in C, matlab, or another language, or permission by instructor. Ideally, students took an introductory neural networks course before.
Readings:
Primary textbook:
TBA
Additional recommended books:
Instructors:
Dr. Sethu Vijayakumar
Dr. Stefan Schaal
Associate Professor
University of Southern California
Ronald Tutor Hall RTH-417
Los Angeles, CA 90089-2520
phone: (213) 740 9418
email: {$ \textrm{sethu@usc.edu} $}
email: {$ \textrm{sschaal@usc.edu} $}
Office Hours:
According to email arrangement with instructors
Academic Integrity:
All students are required to abide by the USC code of Academic Integrity. Violation of that Code will be dealt with as described in SCAMPUS. If you have any questions about the responsibilities of either students, faculty, or graders under this policy, contact the instructor or the Office of Student Conduct.
Disabilities and Academic Accomodations:
Students requesting academic accomodations based on a disability are required to register with Disability Services and Programs (DSP) each semester. A letter of verification for approved accomodations can be obtained from DSP when adequate documentaion is filed. Please be sure the letter is delivered to the instructor (or TA) as early in the semester as possible. DSP is open Monday-Friday, 8:30-5:00. The office is in Student Union 301 and their phone number is (213) 740-0776.
