×

A recurrent neural network for computing pseudoinverse matrices. (English) Zbl 0808.65038

A method for computing the pseudoinverses of matrices is given. The authors make use of a recurrent neural network. The proposed method is a new parallel distributed computational algorithm.
The computations are fast and stable. This should make the method a good choice for real time applications involving inverse kinematic computations in robotics.

MSC:

65F20 Numerical solutions to overdetermined systems, pseudoinverses
65Y05 Parallel numerical computation
70E15 Free motion of a rigid body
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Chen, C.-T., Linear System Theory and Design (1984), Holt, Rinehart: Holt, Rinehart Winston, New York
[2] Yoshikawa, T., Foundations of Robotics: Analysis and Control (1990), MIT Press: MIT Press Cambridge, MA
[3] Kosko, B., Neural Networks and Fuzzy Systems (1992), Prentice Hall: Prentice Hall Englewood Cliffs, NJ
[4] Wang, L. X.; Mendel, J. M., Parallel structured networks for solving a wide variety of matrix algebra problems, Journal of Parallel and Distributed Computing, 14, 236-247 (1992)
[5] Wang, L. X.; Mendel, J. M., Three-dimensional structured networks for matrix equation solving, IEEE Transactions on Computers, 40, 1337-1345 (1991) · Zbl 1395.68129
[6] Cichocki, A.; Unbehauen, R., Neural networks for solving systems of linear equations and related problems, IEEE Transactions on Circuits and Systems, 39, 124-138 (1992) · Zbl 0748.94025
[7] Wang, J., Electronic realization of a recurrent neural network for solving simultaneous linear equations, Electronics Letters, 28, 493-495 (1992)
[8] Wang, J., Recurrent neural networks for solving systems of complexed-valued linear equations, Electronics Letters, 28, 1751-1753 (1992)
[9] Wang, J., Recurrent neural networks for solving linear matrix equations, Computers Math. Applic., 26, 9, 23-34 (1993) · Zbl 0796.65058
[10] Wang, J.; Li, H., Solving simultaneous linear equations using recurrent neural networks, Information Sciences, 76, 255-277 (1993) · Zbl 0803.65055
[11] Samardzija, N.; Waterland, R. L., A neural network for computing eigenvectors and eigenvalues, Biological Cybernetics, 65, 211-214 (1991) · Zbl 0793.68123
[12] Cichocki, A.; Unbehauen, R., Neural networks for computing eigenvalues and eigenvectors, Biological Cybernetics, 68, 155-164 (1992) · Zbl 0769.65015
[13] Wang, J.; Wu, G., Recurrent neural networks for LU decomposition and Cholesky factorization, Mathl. Comput. Modelling, 18, 6, 1-8 (1993) · Zbl 0804.90143
[14] Jang, J.; Lee, S.; Shin, S., An optimization network for matrix inversion, (Neural Information Processing Systems (1988), American Institute of Physics: American Institute of Physics New York), 397-401
[15] Luo, F. L.; Zheng, B., Neural network approach to computing matrix inversion, Applied Mathematics and Computation, 47, 109-120 (1992) · Zbl 0748.65025
[16] Wang, J., A recurrent neural network for real-time matrix inversion, Applied Mathematics and Computation, 55, 23-34 (1993)
[17] Boullion, T.; Odell, P. L., Generalized Inverse Matrices (1971), John Wiley & Sons: John Wiley & Sons New York · Zbl 0223.15002
[18] Wu, G.; Wang, J., A recurrent neural network for manipulator inverse kinematics computation, Orlando, FL. Orlando, FL, Proceedings of 1994 IEEE World Congress on Computational Intelligence (1994), (in press)
[19] Cichocki, A.; Unbehauen, R., Neural Networks for Optimization and Signal Processing (1993), John Wiley & Sons: John Wiley & Sons West Sussex, UK · Zbl 0824.68101
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.