Syllabus
Time and Place:
2:00-3:20 Mondays & Wednesdays, SLH 100
Announcements:
- Nov 28, 2008: Homework 4 is due on Dec 15th.
- Nov 22, 2008: Homework 3 is out, due for submission on Dec 3rd, in class (the day of the final exam).
- Nov 4, 2008: Homework 2 is out, due for submission on Nov 14th, 6pm.
- Oct 6, 2008: Homework 1 is out, due for submission
in class on Oct 15th on Oct 17th (drop it off at RTH 417, or under the door of RTH 401)
- Aug. 2008: Note that the text book has changed, and the course syllabus will be updated according to this new book.
Course Description:
The course will introduce fundamental and advanced techniques of neural computation with statistical neural networks. Skills from this course will be beneficial for applied and basic research in artificial intelligence (e.g., robotics, machine learning, process control), computational neuroscience (e.g., motor control, functional brain modeling) and cognitive sciences (e.g., perception, memory, reasoning). Topics of the course will initially briefly survey classical supervised and unsupervised learning methods, such as backpropagation, radial basis functions, clustering, Kohonen networks, Boltzman machines, and principal components. Afterwards, in accordance with the interests of the participants, modern concepts in learning will be introduced, possibly including nonparametric learning, reinforcement learning, mixtures models, belief networks, minimum description length, maximum likelihood, entropy methods, independent component analysis, support vector machines, gaussian processes, etc.
Class Format:
The course consists of lectures with discussions, reading assignments, and homework assignments using dedicated neural network software in Matlab. Each student will carry out an independent final project in an area subject to the instructor's approval. At the end of the course there will be a short written exam reviewing the basics of the course.
Grading:
- 4 Homework Assignments, each 12.5%
- 1 Project, 30%
- 1 Final Exam, 20%
Prerequisites:
Basic knowledge in linear algebra, calculus, and programming in C (or another language), or permission by instructor.
Textbooks:
- C. M. Bishop, Pattern recognition and machine learning. New York: Springer, 2006.
- Duda, Hart and Stork, 2000, Pattern Classification, Wiley & Sons (optional)
(Note: The following are pre-print chapters of this book. Please do not distribute these chapters outside of our class.)
- For more information on neural networks see:
Neural Networks FAQ
Instructor:
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{sschaal@usc.edu} $}
TA:
Mrinal Kalakrishnan
University of Southern California
Ronald Tutor Hall RTH-417
Los Angeles, CA 90089-2520
phone: (213) 740 6717
email: {$ \textrm{kalakris@usc.edu} $}
Office Hours:
According to email arrangement with instructor {$ \textrm{sschaal@usc.edu} $} or TA {$ \textrm{kalakris@usc.edu} $}.
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.
