Courses: SYSC 576 / EE 456/556: Neural Networks II: Spring 2010
Course Syllabus (pdf)
Class Schedule (pdf)
Assignments
- Reading Assignment 1
- Problem Assignment 1: Fuzzy Systems
- Problem Assignment 2: Build NN model via given data set
Term Project
Readings
(Alphabetical by first author)
- Barto, A.G. (1991), "Connectionist Learning for Control: An Overview" (Chapter 1) and Werbos, P.J., "Overview of Designs and Capabilities" (Chapter 2) from Neural Networks for Control, Miller, Sutton & Werbos, Eds, MIT Press, pp.5-66.
- Jaeger, H. (2002): Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the "echo state network" approach. GMD Report 159, German National Research Center for Information Technology (revised 2005).
- Lendaris, G., Mathia, K. (1996), "Efficient Numerical Inversion Using Multilayer Feedforward Neural Networks," World Congress on Neural Networks 1996, San Diego, California.
- Lendaris, G.G., Shannon, T.T. (1998), "Designing (Approximate) Optimal Controllers via DHP Adaptive Critics & Neural Networks", Draft of Invited Chapter for The Handbook of Applied Computational Intelligence, CRC Press, Padget, Karayianis, & Zadeh, Eds. [book not published]
- Lendaris, G.G, K. Mathia, R. Saeks (1999), "Linear Hopfield Networks and Constrained Optimization," Transactions of Systems, Man Cybernetics, IEEE, Vol. 29, No. 1, pp. 114 - 118, February.
- Lendaris, G.G., Neidhoefer, J.S. (2004), "Guidance in the Use of Adaptive Critics for Control" Ch.4 in Handbook of Learning and Approximate Dynamic Programming, Si, et al, Eds., IEEE Press & Wiley Interscience, pp. 97-124, 2004.
- Lendaris, G.G. (2008), “Higher Level Application of ADP: A Next Phase for the Control Field? IEEE Trans. on Systems, Man, and Cybernetics-Part B, vol 38, no. 4, Aug.
- Lendaris, G.G. (2009), “A Retrospective on Adaptive Dynamic Programming for Control”, IJCNN'2009 (shorter w/similar content 2008 IEEE paper).
- Lewis, F.L. (2006), "Neural Networks in Feedback Control Systems" in Mechanical Engineer’s Handbook, John Wiley, New York.
- Mathia, K., G.G. Lendaris, R. Saeks (1995), "Solving Nonlinear Equations using Recurrent Neural Networks," Proceedings of World Congress on Neural Networks 'R95 (WCNN-95), Washington, DC, Earlbaum/INNS, July.
- Neural Networks for Control (1990), Miller, W.T., R. Sutton, P. Werbos (eds.), MIT Press, Cambridge, MA. [Chapter 5, Narendra]
- Neural Networks for Control (1990), Miller, W.T., R. Sutton, P. Werbos (eds.), MIT Press, Cambridge, MA. [Chapter 12, Nguyen & Widrow]
Notes
LendarisMay2,2008,SeminarTalk,PartI
LendarisMay2,2008,SeminarTalk,Part II
Slides for lecture on May 19:
- Holmstrom, L. (2005), "Designing a Contextually Aware Controller"
- Lendaris, G.G. (2005), "Reinforcement Learning for Intelligent Control, Part 2" [The Frame Problem]
- Kosko, B. (1992), "Fuzzy Systems as Universal Approximators"
Faculty
Graduate assistant: Joshua Hughes (hughesjg@pdx.edu), Harder House, Room 207
Office Hours: Tuesday and Thursday 11:00am to 1:30pm (also available via e-mail appointment)
