Warning: main(/Volumes/duerer/clmc/Sites/settings/prologue.php) [function.main]: failed to open stream: No such file or directory in /Volumes/duerer/cs542/Sites/index.php on line 2
Warning: main() [function.include]: Failed opening '/Volumes/duerer/clmc/Sites/settings/prologue.php' for inclusion (include_path='.:/usr/lib/php') in /Volumes/duerer/cs542/Sites/index.php on line 2
CS542 Neural Computation with Artificial Neural Networks
Warning: main(/Volumes/duerer/clmc/Sites/settings/body1.php) [function.main]: failed to open stream: No such file or directory in /Volumes/duerer/cs542/Sites/index.php on line 8
Warning: main() [function.include]: Failed opening '/Volumes/duerer/clmc/Sites/settings/body1.php' for inclusion (include_path='.:/usr/lib/php') in /Volumes/duerer/cs542/Sites/index.php on line 8
Warning: main(/Volumes/duerer/clmc/Sites/settings/body2.php) [function.main]: failed to open stream: No such file or directory in /Volumes/duerer/cs542/Sites/index.php on line 14
Warning: main() [function.include]: Failed opening '/Volumes/duerer/clmc/Sites/settings/body2.php' for inclusion (include_path='.:/usr/lib/php') in /Volumes/duerer/cs542/Sites/index.php on line 14
CS542: Neural Computation with Artificial Neural Networks (Fall 2005)
Time and Place:
2:00-3:20 Mondays & Wednesdays, SGM 601 (will be changed to HNB 100 later)
Announcements
- Nov.21, 2005: Homework 4 available
- Nov.9, 2005: Homework 3 available
- Oct.21, 2005: Homework 2 available
- Sept.26, 2005: Homework 1
available (pdf).
- Aug.24, 2005: Matlab primer here (pdf
file)
- Aug.24, 2005: Class mailing
list is ready. If anyone not already on it wishes to be included,
please send e-mail to Dr. Schaal
Description:
The course will introduce fundamental and advanced techniques of
computation and adaptation in networks of distributed interconnected
processing unit. 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 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%
Note: Every homework assignment can be handed in a second
time to improve the score, after it had been handed in on time
initially. Every homework assignment will also provide the chance to
get bonus points. Bonus points cannot be obtained in the
second hand-in anymore.
Prerequisites:
Basic knowledge in linear algebra, calculus, and programming in C (or
another language), or permission by instructor.
Textbooks:
- Neural Networks for Pattern Recognition (Bishop, C.M., 1995, Oxford
University Press)
- Introduction to the Theory of Neural Computation (Hertz, J. ,Krogh,
A., Palmer, R. G., 1991, Addision Wesley) (optional)
- 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
Hedco Neurosciences Building HNB-103
Los Angeles, CA 90089-2520
phone: (213) 740 9418
email: sschaal@usc.edu
TA:
Jo-Anne Ting
University of Southern California
Hedco Neurosciences Building
Los Angeles, CA 90089
phone: (213) 740 6717
email: joanneti@usc.edu
Office Hours:
According to email arrangement with instructor
(sschaal@usc.edu) or TA
(joanneti@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.
Warning: main(/Volumes/duerer/clmc/Sites/settings/epilogue.php) [function.main]: failed to open stream: No such file or directory in /Volumes/duerer/cs542/Sites/index.php on line 162
Warning: main() [function.include]: Failed opening '/Volumes/duerer/clmc/Sites/settings/epilogue.php' for inclusion (include_path='.:/usr/lib/php') in /Volumes/duerer/cs542/Sites/index.php on line 162