Dynamic subgrouping in RTRL provides a faster O(N2) algorithm

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 6, Issue , 2000, Pages 3418-3421

  Euliano, Neil R ^a   Principe, Jose C ^a  

^a UNIVERSITY OF FLORIDA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ELECTRICAL ENGINEERING; APPROXIMATION THEORY; BACKPROPAGATION; COMPUTATIONAL COMPLEXITY; ESTIMATION; GREEN'S FUNCTION; ITERATIVE METHODS; LEARNING ALGORITHMS; MATRIX ALGEBRA; NONLINEAR SYSTEMS; REAL TIME SYSTEMS; SENSITIVITY ANALYSIS; SET THEORY;

HEBBIAN; LOCAL APPROXIMATION; PROCESSING ELEMENTS; REAL-TIME RECURRENT LEARNING;

SIGNAL PROCESSING; RECURRENT NEURAL NETWORKS;

DYNAMIC SUBGROUPING; HEBBIAN LEARNING; PROCESSING ELEMENTS; REAL TIME RECURRENT LEARNING; SENSITIVITY MATRIX;

EID: 0033678386     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.860135     Document Type: Conference Paper

References (13)

1. Fernandez B., Parios A., Tsai W., (1990) Nonlinear dynamic system identification using ANNs, I. J. Conf. Neural networks, vol II, 133-141, San Diego.
2. Haykin, S. (1994), Neural Networks, A Comprehensive Foundation. Macmillan College Publishing Company, New York. pp. 521-525.
3. Narendra and Parthasarathy (1991) Gradient methods for the optimization of dynamical systems using neural nets, IEEE Trans. Neural Net, vol2, #2, 252-262.
4. Pearlmutter, B. (1995) Gradient Calculations for Dynamic Recurrent Neural Networks: A Survey. IEEE Trans. Neural Networks, Vol. 6, No 3, pp. 1212-1228.
5. Puskorius G., Feldkamp L. (1994) NeuroControl of nonlinear systems with Kaiman filter trained recurrent networks, IEEE Trans. Neural Net., vol 5, #2, 279-297.
6. Puskorius G., Feldkamp L (1994) Truncated backpropagation through time and Kaiman filter training for neurocontrol, Int. J. Conf. Neural Nets, vol 4 2488-2493.
7. Schmidhuber, J. (1992) A Fixed Size Storage 0 (n3) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks. Neural Computation 4, pp. 243-248.
8. Sun, G. Z, Chen, H. H. & Lee, Y. C. (1992) Green's Function Method for Fast On-line Learning Algorithm of Recurrent Neural Networks. In NIPS 4, pp. 333-340.
9. Werbos, P. (1990) Backpropagation through time: what it does and how to do it, Proc. IEEE 78, 1550-1560.
10. Williams, R. J. & Peng, J. (1990) An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories. Neural Computation 1, pp. 490-501.
11. Williams, R. J. & Zipser, D. (1989) A learning Algorithm for Continually Running Fully Recurrent Neural Networks. In Neural Computation, Number 1, pp. 270-280.
12. Zipser, D. (1989) A Subgrouping Strategy that Reduces Complexity and Speeds Up Learning in Recurrent Networks. Neural Computation 1, pp. 552-558.
13. Zipser, D. (1990) Subgrouping Reduces Complexity and Speeds up Learning in Recurrent Networks. In NIPS 2, pp. 638-641.