|
|
Courses: EE456/556, SYSC 576: Artificial Neural Networks II: Winter 2007
-
Assignments
- Reading Assignment 1
- Problem Assignment 1: Surface construction via FAMs
- Problem Assignment 2: Build NN model via given data set
- Problem Assignment 2: DATA SET
-
Term Project
- Candidate Term Project Ideas
-
Readings
- Barto, A.G., "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, 1991.
- Lendaris, G.G. & T.T. Shannon, 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. & J.S. Neidhoefer, 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.
- George G. Lendaris, "Experience-Based Identification and Control via Higher-Level Learning and Context Discernment", Proceedings of the International Joint Conference on Neural Networks 2006 (IJCNN'06), Vancouver, B.C., July
- Holmstrom, Lars A., Roberto A. Santiago, George G. Lendaris, "On-Line System Identification Using Context Discernment," Proceedings of the International Joint Conference on Neural Networks 2005 (IJCNN'05), Montreal, July.
- Neural Networks for Control Chapter 5 (Narendra)
- Neural Networks for Control Chapter 12 (Nguyen & Widrow)
- Lendaris, G.G, K. Mathia, & R. Saeks, (1999) "Linear Hopfield Networks and Constrained Optimization," Transactions of Systems, Man Cybernetics, IEEE, vol xxx.
- Bart Kosko, (1992) "Fuzzy Systems as Universal Approximators"
-
Notes
- In-class PowerPoint presentation on Wed., Jan. 10, 2007, entitled "Experience-Based Identification & Control via Higher-Level Reinforcement Learning".
- In-class PowerPoint presentation on Mon., Jan. 22nd and Mon., Jan. 29th, 2007, entitled "Reinforcement Learning for Intelligent Control".
-
In-class PowerPoint presentation on Wed., Jan. 24, 2007, entitled "Implementing DHP in Software: Taking Control of the Pole Cart System".
-
Faculty
- George G. Lendaris
- Graduate Assistant: Lars Holmstrom (email:larsh(at)pdx.edu office:SYSC207)
Links
|
|
 |
