Gradient-based parameter optimization for systems containing discrete-valued functions

International Journal of Robust and Nonlinear Control

Volumn 12, Issue 11, 2002, Pages 1009-1028

  Wilson, Edward ^a   Rock, Stephen M ^b  

^a Intellization   (United States)

^b 496 Lomita Mall   (United States)

Author keywords

Backpropagation; Hard limiter; Neural network; Optimization

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; BACKPROPAGATION; DECISION MAKING; DIFFERENTIATION (CALCULUS); GRADIENT METHODS; LARGE SCALE SYSTEMS; MULTILAYER NEURAL NETWORKS; OPTIMIZATION; PARAMETER ESTIMATION; PROBLEM SOLVING; SPURIOUS SIGNAL NOISE;

GRADIENT-BASED PARAMETER OPTIMIZATION; NOISY BACKPROPAGATION ALGORITHMS;

DISCRETE TIME CONTROL SYSTEMS;

EID: 0036738766     PISSN: 10498923     EISSN: None     Source Type: Journal    
DOI: 10.1002/rnc.729     Document Type: Article

References (22)

1. Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error propagation. Parallel Distributed Processing. The MIT Press: Cambridge, MA 02142, 1986; 318.
2. Werbos PJ. Beyond Regression: new tools for prediction and analysis in the behavioral sciences. PhD Thesis, Harvard University, Cambridge, MA 02142, 1974.
3. Hoff ME Jr. Learning phenomena in networks of adaptive switching circuits. PhD Thesis, Stanford University, Stanford, CA 94305, 1962. Tech. Rep. 1556-1, Stanford Electron. Labs.
4. Widrow B, Lehr MA. 30 years of adaptive neural networks: Perceptron, MADALINE, and backpropagation. Proceedings of the IEEE 1990; 78(9):1415-1442.
5. Rosenblatt F. Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Spartan Books: Washington, DC, 1962.
6. Winter R, Widrow B. Madaline Rule II: a training algorithm for neural networks. IEEE International Conference on Neural Networks vol. 1 1988; 401-408.
7. Bartlett PL, Downs T. Using random weights to train multilayer networks of hard-limiting units. IEEE Transactions on Neural Networks 1992; 3(2):202-210.
8. Widrow B. A study of rough amplitude quantization by means of Nyquist sampling theory. IRE Transactions of the Professional Group on Circuit Theory 1956; CT-3(4):266-276.
9. An G. The effects of adding noise during backpropagation training on generalization performance. Neural Computation 1996; 8(3):643-674.
10. Murray AF, Edwards PJ Enhanced mlp performance and fault tolerance resulting from synaptic weight noise during training. IEEE Transactions on Neural Networks 1994; 5(5):792-802.
11. Wilson E. Experiments in neural network control of a free-flying space robot. PhD Thesis, Stanford University, Stanford, CA 94305, 1995.
12. Wilson E. Experiments in neural network control of a free-flying space robot. Proceedings of the Fifth Workshop on Neural Networks: Academic/Industrial/NASA/Defense 1993; 204-209; SPIE. proceedings of the SPIE, vol. 2204.
13. Wilson E. Backpropagation learning for systems with discrete-valued functions. Proceedings of the World Congress on Neural Networks, vol. 3, 1994; 332-339.
14. Bryson AE Jr., Ho YC. Applied Optimal Control. Hemisphere Publishing Corporation: New York, NY, 1975.
15. MATLAB is a registered trademark of The MathWorks, Inc., 24 Prime Park Way, Natick, MA 01760, 508-647-7000.
16. Wilson E. Matlab source code for noisy backpropagation example. Available at http://sun-valley.stanford.edu, 1997.
17. Weigend AS, Huberman BA, Rumelhart DE. Predicting the future: a connectionist approach. International Journal of Neural Systems 1990; 1(3):193-209.
18. Wilson E, Rock SM. Experiments in control of a free-flying space robot using fully-connected neural networks. Proceedings of the World Congress on Neural Networks vol.3, 1993; 157-162.
19. Wertz JR, editor. Spacecraft Attitude Determination and Control. Kluwer Academic Publishers: Boston, MA, 1978.
20. Ullman MA. Experiments in autonomous navigation and control of multi-manipulator, free-flying space robots. PhD Thesis, Stanford University, Stanford, CA 94305, 1993.
21. Wilson E, Rock SM. Neural network control of a free-flying space robot. Simulation 1995; 65(2):103-115.
22. Wilson E, Rock SM. Reconfigurable control of a free-flying space robot using neural networks. Proceedings of the American Control Conference, 1995.