3 credit points
Synopsis This course focuses on theory and the most commonly used methods for neural network design, and their relation to machine learning. After the course, students will learn to design suitable neural networks in pattern recognition and nonlinear system modelling, or improve their design in these applications. The course is suitable for graduate students, especially for students who is engaged in or will be engaged in the study of neural networks and machine learning field.
Outcomes Upon completion of the course, students are able to understand basic artificial neural models and their design methods, including lmaster the principle of Multi-layer Perceptrons and Radial Basis Function Networks, and the basic and improved parameter learning algorithms; lmaster the non-structure design methods of common feed-forward networks including optimal stopping, active learning, neural network ensembles, etc.; lmaster the structure design methods of common feed-forward networks including pruning, constructing, and evolution algorithms; lunderstand what and how those factors affect the generalization ability of a neural network; lunderstand the principle and design methods of some common feed-back neural networks including Hopfield neural networks and self-organizing feature map; luse neural networks to solve problems such as pattern recognition and function approximation.
Assessment There will be two in-term projects, and a final the last day of class. You are required to complete two class projects. The choice of the topic is up to you so long as it clearly pertains to the course materials. We expect a five page write-up about each of the projects, which should clearly and succinctly describe the project goal, methods, and your results. Your overall grade will be determined roughly as follows:
Chief examiner(s) Professor Haikun Wei
|
Teachers
Research areas
Neural network theory and applications, including neural singularity and learning dynamics analysis, pattern classification, neural network based nonlinear system modeling, and other related neural network applications.
Education
PhD (Automatic Control), Southeast University (2000)
M.Ec (Automatic Control), Southeast University (1997)
B.Sc (Industry Automation), North China Universityof Technology (1994)
Employment
2009-present | School of Automation, Southeast University, Professor & Vice Dean |
2002-2009 | |
2000-2002 | Department of Automatic Control, Southeast University, Assistant Professor |
Part of Publications from 2005:
1.Haikun Wei. Theory and Methods for Neural Networks Structure Design. National Defence Industry Press, Beijing, 2005.2. (Book in Chinese).
2.Changsheng Jiang, Congqing Wang, Haikun Wei, Mou Chen. Intelligent control and its applications. Science Press, Beijing, 2007.7.
3.Haikun Wei and Shun-ichi Amari. “Dynamics of Learning near Singularity in Radial Basis Function Networks”, Neural Networks, 2008,21(7), 989-1005 (Regular paper).
4.Haikun Wei, Jun Zhang, Florent Cousseau, Tomiko Ozeki, and Shun-ichi Amari. “Dynamics of Learning Near Singularities in Layered Networks”. Neural Computation, 2008, 20(3), 813-843.
5.Xinming Jin and Haikun Wei. “Scenario-based comparison and evaluation: issues of current business process modelling languages”, Proceedings of the I MECH E Part B Journal of Engineering Manufacture, 2006, 220 (9), 1527-1538.
6.Haikun Wei and Shun-ichi Amari. “Eigenvalue Analysis on Singularity in RBF networks”, Proc. IJCNN, 2007.
7.Haikun Wei and Shun-ichi Amari. “Online Learning Dynamics of Radial Basis Function Neural Networks near the Singularity”. Proc. IJCNN, 2006.
Contact Information
Address:
Si Pai Lou 2#
China
Tel.: 025-83794766
E-mail: hkwei@seu.edu.cn