Trajectory generation and modulation using dynamic neural networks

IEEE Transactions on Neural Networks

Volumn 14, Issue 3, 2003, Pages 520-533

  Zegers, Pablo ^a   Sundareshan, Malur K ^b,c  

^a UNIVERSIDAD DE LOS ANDES   (Chile)

^b University of Arizona   (United States)

^c INSTITUTE OF GEOLOGY AND GEOPHYSICS   (China)

Author keywords

Dynamic neural network (DNN); Recurrent neural network (RNN); Trajectory generation; Trajectory modulation

Indexed keywords

COMPUTATIONAL COMPLEXITY; CONTROL SYSTEM SYNTHESIS; CONVERGENCE OF NUMERICAL METHODS; DIFFERENTIAL EQUATIONS; FEEDBACK CONTROL; FEEDFORWARD NEURAL NETWORKS; LEARNING SYSTEMS; NONLINEAR EQUATIONS; RELAY CONTROL SYSTEMS; TRAJECTORIES;

DYNAMIC NEURAL NETWORK; NONRECURRENT NEURAL NETWORK; TEMPORAL LEARNING; TRAJECTORY GENERATION; TRAJECTORY MODULATION;

RECURRENT NEURAL NETWORKS;

EID: 0037507284     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2003.810603     Document Type: Article

References (49)

1. A. Karakasoglu, S. I. Sudharsanan, and M. K. Sundareshan, "Identification and decentralized adaptive control using dynamical neural networks with application to robotic manipulators," IEEE Trans. Neural Networks, vol. 4, pp. 919-930, Nov. 1993.
2. K. S. Narendra and A. Annaswamy, Stable Adaptive Systems. Engelwood Cliffs, NJ: Prentice-Hall, 1989.
3. F. Boe and B. Hannaford, "On-line improvement of speed and tracking performance on repetitive paths," IEEE Trans. Contr. Syst. Technol., vol. 6, pp. 350-358, May 1998.
4. Y. M. Park, M. S. Choi, and K. Y. Lee, "An optimal tracking neurocontroller for nonlinear dynamic systems," IEEE Trans. Neural Networks, vol. 7, pp. 1099-1110, Sept. 1996.
5. A. N. Kolmogorov and S. V. Fomin, Introductory Real Analysis. New York: Dover, 1970.
6. G. Cybenko, "Approximation by superpositions of a sigmoidal function," Math. Contr., Signals, Syst., vol. 2, pp. 303-314, 1989.
7. K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal function approximators," Neural Networks, vol. 2, pp. 359-366, 1999.
8. K. I. Funahashi, "On the approximate realization of continuous mappings by neural networks," Neural Networks, vol. 2, pp. 183-192, 1989.
9. T. Poggio and F. Girosi, "Regularization algorithms for learning that are equivalent to multilayer networks," Science, vol. 247, pp. 978-982, 1990.
10. V. N. Vapnik, The Nature of Statistical Learning. New York: Springer-Verlag, 1995.
11. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations of backpropagation errors," Nature, vol. 323, pp. 533-536, 1986.
12. A. H. Kramer and A. Sangiovanni-Vincentelli, "Efficient parallel learning algorithms for neural networks," in Advances in Neural Information Processing Systems 1. San Mateo, CA: Morgan Kaufmann, 1989, pp. 40-48.
13. B. Verma, "Fast training of multilayer perceptrons," IEEE Trans. Neural Networks, vol. 2, pp. 1314-1320, Sept. 1997.
14. N. N. Schraudolph, "A fast compact approximation of the exponential function," Neural Comput., vol. 11, pp. 853-862, 1999.
15. E. B. Baum, "Neural net algorithms that learn in polynomial time from examples and queries," IEEE Trans. Neural Networks, vol. 2, pp. 5-19, Jan. 1991.
16. K. I. Funahashi and Y. Nakamura, "Approximation of dynamical systems by continuous time recurrent neural networks," Neural Networks, vol. 6, pp. 801-806, 1993.
17. F. J. Pineda, "Generalization of backpropagation to recurrent neural networks," Phys. Rev. Lett., vol. 59, no. 19, pp. 2229-2232, Nov. 1987.
18. B. A. Pearlmutter, "Learning state-space trajectories in recurrent neural networks," Neural Comput., vol. 1, pp. 263-269, 1989.
19. R. J. William and D. Zipser, "A learning algorithm for continually running fully recurrent neural networks," Neural Comput., vol. 1, pp. 270-280, 1989.
20. P. J. Werbos, "Backpropagation through time: What it does and how to do it," Proc. IEEE, vol. 78, pp. 1550-1560, Oct. 1990.
21. R. J. Williams and J. Peng, "An efficient gradient-based algorithm for on-line training of recurrent network trajectories," Neural Comput., vol. 2, pp. 490-501, 1990.
22. B. A. Pearlmutter, "Gradient calculations for dynamic recurrent neural networks: A survey," IEEE Trans. Neural Networks, vol. 6, pp. 1212-1228, Sept. 1995.
23. Y. Fang and T. J. Sejnowski, "Faster learning for dynamic recurrent backpropagation," Neural Comput., vol. 2, pp. 270-273, 1990.
24. N. B. Toomarian and J. Barhen, "Learning a trajectory using adjoint functions and teacher forcing," Neural Networks, vol. 5, pp. 473-484, 1992.
25. T. Catfolis, "A method for improving the real-time recurrent learning algorithm," Neural Networks, vol. 6, pp. 807-821, 1993.
26. D. T. Lin, J. E. Dayhoff, and P. A. Ligomenides, "Trajectory production with the adaptive time-delay neural network," Neural Networks, vol. 8, no. 3, pp. 447-461, 1995.
27. O. Olurotimi, "Recurrent neural network training with feedforward complexity," IEEE Trans. Neural Networks, vol. 5, pp. 185-197, Mar. 1994.
28. B. Cohen, D. Saad, and E. Marom, "Efficient training of recurrent neural networks with time delays," Neural Networks, vol. 10, no. 1, pp. 51-59, 1997.
29. M. Galicki, L. Leistritz, and H. White, "Learning continuous trajectories in recurrent neural networks with time dependent weights," IEEE Trans. Neural Networks, vol. 10, pp. 741-756, July 1999.
30. M. Bianchini, M. Gori, and M. Maggini, "On the problem of local minima in recurrent neural networks," IEEE Trans. Neural Networks, vol. 5, pp. 167-177, Mar. 1994.
31. Y. Bengio, P. Simard, and P. Frasconi, "Learning long term dependencies with gradient descent in difficult," IEEE Trans. Neural Networks, vol. 5, pp. 157-166, Mar. 1994.
32. P. J. Angeline, G. M. Saunders, and J. B. Pollack, "An evolutionary algorithm that constructs recurrent neural networks," IEEE Trans. Neural Networks, vol. 5, pp. 54-65, Jan. 1994.
33. M. K. Sundareshan and T. A. Condarcure, "Recurrent neural network training by a learning automation approach for trajectory learning and control system design," IEEE Trans. Neural Networks, vol. 9, pp. 1-15, Jan. 1998.
34. J. E. Dayhoff, P. J. Palmadesso, F. Richards, and D. T. Lin, "Patterns of dynamic activity and timing in neural network processing," in Neural Networks and Pattern Recognition, O. Omidvar and J. Dayhoff, Eds. New York: Academic, 1998.
35. M. K. Sundareshan, Y. C. Wong, and T. Condarcure, "Training algorithms for recurrent neural nets that eliminate the need for computation of error gradients with applications to trajectory production problems," in Recurrent Neural Networks: Design and Applications, L. Medsker and L. C. Jain, Eds. Boca Raton, FL: CRC, 1999.
36. A. Ruiz, D. H. Owens, and S. Townley, "Existence, learning and replication of periodic motions in recurrent neural networks," IEEE Trans. Neural Networks, vol. 9, pp. 651-661, July 1998.
37. S. Townley, A. Ilchmann, M. G. Weiss, W. McClements, A. C. Ruiz, D. H. Owens, and D. Pratzel-Wolters, "Existence and learning of oscillations in recurrent neural networks," IEEE Trans. Neural Networks, vol. 11, pp. 205-214, Jan. 2000.
38. J. J. Hopfield, "Neurons with graded response have collective computational properties like those of two-state neurons," Proc. Nat. Academy Sci. USA, vol. 79, pp. 2554-2558, 1984.
39. S. I. Sudharsanan and M. K. Sundareshan, "Supervised training of dynamical neural networks for associative memory design and identification of nonlinear maps," Int. J. Neural Syst., vol. 5, no. 3, pp. 165-180, Sept. 1994.
40. P. Zegers and M. K. Sundareshan, "Periodic motions, mapping ordered sequences and training dynamic neural networks to generate continuous and discontinuous trajectories," in Proc. Int. Joint Conf. Neural Networks, Session WA-1, Como, Italy, 2000, pp. 619-625.
41. Y. Z. Tsypkin, Relay Control Systems. Cambridge, U.K.: Cambridge Univ. Press, 1984.
42. K. J. Astrom and T. Hagglund, "Automatic tuning of simple regulators," in Proc. IFAC 9th World Congr., 1984, pp. 1867-1872.
43. K. J. AstromHagglund, "Automatic tuning of simple regulators with specifications on phase and amplitude margins," Automatica, vol. 20, no. 5, pp. 645-651, 1984.
44. K. J. Astrom and B. Wittenmark, Adaptive Control. Reading, MA: Addison-Wesley, 1995.
45. T. Kailath, Linear Systems. Englewood Cliffs, NJ: Prentice-Hall, 1980.
46. V. Cherkassky and F. Mulier, Learning from Data: Concepts, Theory and Methods. New York: Wiley, 1998.
47. D. G. Hagner, M. H. Hassoun, and P. B. Watta, "Comparison of recurrent neural networks for trajectory generation," in Recurrent Neural Networks: Design and Applications, L. Medsker and L. C. Jain, Eds. Boca Raton, FL: CRC, 1999.
48. K. Ogata, Discrete-Time Control Systems. Englewood Cliffs, NJ: Prentice-Hall, 1987.
49. P. Zegers, "Some new results on the architecture training process and estimation error bounds for learning machines," Ph.D. dissertation, Univ. Arizona, 2002.