Course
| code | EE717 |
| credit_hours | 3 |
| title | Neural Networks and Neurocontrol |
| arbic title | |
| prequisites | None |
| credit hours | 3 |
| Description/Outcomes | Elementary biophysical background for signal propagation in natural and neural systems. Artificial Neural networks (ANN). Hopfield. Feed forward. Learning techniques of McCulloch and Pitts Model. Connectionist model. The random neural network model. Associative memory. Learning algorithm application to Control engineering. |
| arabic Description/Outcomes | |
| objectives | The student should be able to: Learn the graduate new techniques in control system. Update the graduate an objective on neural networks and how it is applied in control system. |
| arabic objectives | |
| ref. books | R. Beale and T. Jackson, “Neural computing: An introductionâ€, Institute of Physics Publishing, 1990. J. Hertz, A Krogh and R.G. Palmer, “Introduction to the Theory of Neural Computationâ€, Addison Wesley, Redwood City, CA 1992. M. N. O Ravn, N. K. Hansen, "Neural Networks for Modeling and Control of Dynamic Systems", 2008. |
| arabic ref. books | |
| textbook | |
| arabic textbook | |
| objective set | |
| content set | |
Course Content
| content serial |
Description |
| 1 |
Introduction.
|
| 2 |
Neuron Model.
|
| 3 |
Perception.
|
| 4 |
Supervised Hebbian learning.
|
| 5 |
Performance Optimization.
|
| 6 |
Widrow – Hoff Learning.
|
| 7 |
Back propagation.
|
| 8 |
Variations on Back Propagation.
|
| 9 |
Associative learning.
|
| 10 |
Associative learning.
|
| 11 |
Competitive Networks.
|
| 12 |
Hopfield Network.
|
| 13 |
Matlab Tool Box.
|
| 14 |
Matlab Tool Box.
|
| 15 |
Matlab Tool Box.
|
| 16 |
Final Exam.
|