Abstract
The Qubit neuron model is a new non-standard computing scheme that has been found by simulations to have efficient processing abilities. In this paper we investigate the usefulness of the model for a non linear kinetic control application of an inverted pendulum on a cart. Simulations show that a neural network based on Qubit neurons would swing up and stabilize the pendulum, yet it also requires a shorter range over which the cart moves as compared to a conventional neural network model.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Abbreviations
- CNN:
-
conventional neural network
- QBP:
-
quantum back propagation
- QNN:
-
qubit neural network
References
D. Deutsch R. Jozsa (1992) ArticleTitleRapid solution of problems by quantum computation Proceedings of Royal Society of London, series A 439 553–558 Occurrence Handle1992RSPSA.439..553D Occurrence Handle94d:81011
Shor, P. W. Algorithm for quantum computation: discrete logarithms and factoring, In: Proceedings of the 35th Annual IEEE Symposium on Foundations of Computer Science, pp. 124–134, 1994.
S.C. Kak (1995) ArticleTitleOn quantum neural computing Information Science 83 143–163 Occurrence Handle10.1016/0020-0255(94)00095-S
M. Peruš (1996) ArticleTitleNeuro-quantum parallelism in brain-mind and computers Informatica. 20 173–183
Peruš, M., Bischof, H. and Kiong, L. C. Quantum-implemented selective reconstruction of high-resolution images, xxx.lanl.gov/pdf/quant-ph/0401016 (2004).
Matsui, N., Takai, M. and Nishimura, H. A network model based on qubit-like neuron corresponding to quantum circuit, IEICE Trans., J81-A 12 (1998), 1687–1692 (in Japanese) Electronics and Communications in Japan, Part 3 83 (10) (2000), 67–73.
Kouda, N., Matsui, N. and Nishimura, H. A multi-layered feed-forward network based on Qubit neuron model, IEICE Trans., J85-D-II 4 (2002), 641–648 (in Japanese) Systems and Computers in Japan, 35 (13) (2004), 43–51.
Kouda, N., Matsui, N. and Nishimura, H. Learning Performance of Neuron Model based on Quantum Superposition, In: Proceedings of the 2000 IEEE International Workshop on Robot and Human Interactive Communication, pp. 112–117, Osaka, IEEE, 2000.
N. Kouda N. Matsui H. Nishimura (2002) ArticleTitleImage compression by layered quantum neural networks Neural Processing Letters 16 IssueID1 67–80 Occurrence Handle10.1023/A:1019708909383
Kouda, N., Matsui, N., Nishimura, H. and Peper, F. Qubit Neural Network and Its Efficiency In: Proceedings of Knowledge- Based Intelligent Information Engineering Systems (KES2003), LNAI-2774, pp. 304–310, Springer-Verlag, 2003.
Kouda, N., Matsui, N., Nishimura, H. and Peper, F. Qubit Neural Network and Its Learning Efficiency, Neural Computing and Applications, Springer-Verlag (online published, DOI:10.1007/s00521-004-0446-8, 2005).
H.D. Patiño R. Caralli B.R. Kuchen (2003) ArticleTitleNeural networks for advanced control of robot manipulators IEEE Trans. Neural Networks 13 343–354
Tolat, V. V. and Widrow, B. An adaptive ‘broom balancer’ with visual inputs, In: Proceedings of the Int. Conf. on Neural Networks, pp. 641–647, IEEE Press, II, 1988.
Kawada, K., Yamamoto, T. and Mada, Y. A Design of Evolutionary Neural-Net Based Controllers for an Inverted Pendulum, In: Proceedings of the SICE Annual Conference 2003, pp. 2825–2828, Fukui, SICE, 2003.
D.E. Rumelhart G.E. Hinton R.J. Williams (1986) Learning internal representations by error propagation D.E Rumelhart J.L. McClelland (Eds) Parallel Distributed Processing: Explorations in the Microstructures of Cognition, 1. MIT Press Cambridge, MA 318–362
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
kouda, N., Matsui, N., Nishimura, H. et al. An Examination of Qubit Neural Network in Controlling an Inverted Pendulum. Neural Process Lett 22, 277–290 (2005). https://doi.org/10.1007/s11063-005-8337-2
Issue Date:
DOI: https://doi.org/10.1007/s11063-005-8337-2