Hardware Implementation of a Pulse Density Neural Network Using Simultaneous Perturbation Learning Rule

Analog Integrated Circuits and Signal Processing

Volumn 18, Issue 2-3, 1999, Pages 153-162

  Maeda, Yutaka ^a,b   Nakazawa, Atsushi ^a   Kanata, Yakichi ^a  

^a KANSAI UNIVERSITY   (Japan)

^b UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Neural networks; Pulse density; Simultaneous perturbation

Indexed keywords

BACKPROPAGATION; KNOWLEDGE BASED SYSTEMS; LEARNING SYSTEMS; PERTURBATION TECHNIQUES;

PULSE DENSITY NEURAL NETWORKS;

NEURAL NETWORKS;

EID: 0038397272     PISSN: 09251030     EISSN: None     Source Type: Journal    
DOI: 10.1023/a:1008355204358     Document Type: Article

References (18)

1. B. J. Sheu and J Choi, "Neural information processing and VLSI." Kluwer Academic Publishers, 1995.
2. S. M. Fakhraie and K. C. Smith, "VLSI-Compatible implementation for artificial neural networks." Kluwer Academic Publishers, 1997.
3. M. Jabri and B. Flower, "Weight perturbation : An optimal architecture and learning technique for analog VLSI feed forward and recurrent multi layer networks." IEEE Trans. on Neural Networks 3(1), pp. 154-157, 1992.
4. A. J. Montalvo, R. S. Gyurcsik, and J. J. Paulos, "Toward a general-purpose analog VLSI neural network with on-chip learning." IEEE Trans. on Neural Networks 8(2), pp. 413-423, 1997.
5. J. C. Spall, "A schismatic approximation technique for generating maximum likelihood parameter estimates." Proc. of the 1987 American Control Conference pp. 1161-1167, 1987.
6. J. C. Spall, "Multivariable schismatic approximation using a simultaneous perturbation gradient approximation." IEEE Trans. AC-37, pp. 332-341, 1992.
7. J. Alespector, R. Meir, B. Yuhas, A. Jayakumar, and D. Lippe, "A parallel gradient descent method for learning in analog VLSI neural networks." in S. J. Hanson, J. D. Cowan and C. Lee (eds.), Advances in neural information processing systems 5. Morgan Kaufmann Publisher, pp. 836-844, 1993.
8. G. Cauwenberghs, "A fast schismatic error-descent algorithm for supervised learning and optimization." in S. J. Hanson, J. D. Cowan and C. Lee (eds.), Advances in neural information processing systems 5. Morgan Kaufmann Publisher, pp. 244-251, 1993.
9. Y. Maeda and Y. Kanata, "Learning rules for recurrent neural networks using perturbation and their application to neurocontrol." Trans. of the Institute of Electrical Engineers of Japan 113-C, pp. 402-408 (in Japanese), 1993.
10. Y. Maeda and Y. Kanata, "A learning rule of neural networks for neuro-controller." Proc. of the 1995 World Congress of Neural Networks 2, pp. II-402-II-405, 1995.
11. Y. Maeda and R. J. P. de Figueiredo, "Learning rules for neuro-controller via simultaneous perturbation." IEEE Trans. on Neural Networks 8, pp. 1119-1130, 1997.
12. Y. Maeda, H. Hirano, and Y. Kanata, "A learning rule of neural networks via simultaneous perturbation and its hardware implementation." Neural Networks 8, pp. 251-259, 1995.
13. G. Cauwenberghs, "An analog VLSI recurrent neural network learning a continuous-time trajectory." IEEE Trans. on Neural Networks 7(2), pp. 346-361, 1996.
14. E. I. El-Masry, H. Yang, and M. A. Yakout, "Implementations of artificial neural networks using current-mode pulse width modulation technique." IEEE Trans. on Neural Networks 8(3), pp. 532-548, 1997.
15. A. F. Murray, D. D. Corso, and L. Tarssenko, "Pulse-stream VLSI neural networks mixing analog and digital techniques." IEEE Trans. on Neural Networks 2(2), pp. 193-204, 1991.
16. H. Eguchi, T. Furuta, H. Horiguchi, and S. Oteki, "Neuron model utilizing pulse density with learning circuits." IEICE Technical Report 90, pp. 63-70, (in Japanese) 1990.
17. Y. Maeda, "Time difference simultaneous perturbation method." ELECTRONICS LETTERS 32, pp. 1016-1017, 1996.
18. J. C. Spall, "A one-measurement form of simultaneous perturbation schismatic approximation." Automatica 33, pp. 109-112, 1997.