Performance of Qubit Neural Network in Chaotic Time Series Forecasting

详细信息    查看全文

• 关键词：Quantum information processing ; Qubit ; Neural network ; Chaotic time series forecasting
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9949
• 期：1
• 页码：253-260
• 全文大小：1,704 KB
• 参考文献：1.Manju, A., Nigam, M.J.: Applications of quantum inspired computational intelligence: a survey. Artif. Intell. Rev. 42(1), 79–156 (2014)CrossRef
  2.Kak, S.C.: On quantum neural computing. Inf. Sci. 83(3), 143–160 (1995)CrossRef
  3.Perus, M.: Neuro-quantum parallelism in brain-mind and computers. Informatica (Ljubljana) 20(2), 173–184 (1996)
  4.Matsui, N., Takai, M., Nishimura, H.: A network model based on qubitlike neuron corresponding to quantum circuit. Electron. Commun. Jpn Part III Fund. Electron. Sci. 83(10), 67–73 (2000)CrossRef
  5.Kouda, N., Matsui, N., Nishimura, H.: Image compression by layered quantum neural networks. Neural Process. Lett. 16, 67–80 (2002)CrossRef MATH
  6.Kouda, N., Matsui, N., Nishimura, H.: A multilayered feed-forward network based on qubit neuron model. Syst. Comput. Jpn 35(13), 43–51 (2004)CrossRef
  7.Kouda, N., Matsui, N., Nishimura, H., Peper, F.: Qubit neural network and its learning efficiency. Neural Comput. Appl. 14(2), 114–121 (2005)CrossRef
  8.Kouda, N., Matsui, N., Nishimura, H., Peper, F.: An examination of qubit neural network in controlling an inverted pendulum. Neural Process. Lett. 22(3), 277–290 (2005)CrossRef
  9.Matsui, N., Nishimura, H., Isokawa, T.: Qubit neural networks: its performance and applications. In: Nitta, T. (ed.) Complex-Valued Neural Networks: Utilizing High-Dimensional Parameters, chap. XIII, pp. 325–351. Information Science Reference, Hershey, New York (2009)
  10.Kido, K.: Short-term prediction on chaotic time-series using neurocomputing. In: Proceedings of the 1st Western Pacific and 3rd Australia-Japan Workshop, pp. 278–284 (1999)
  11.Frank, R.J., Davey, N., Hunt, S.P.: Time series prediction and neural networks. J. Intell. Robot. Syst. 31(1–3), 91–103 (2001)CrossRef MATH
  12.Han, M., Xi, J., Xu, S., Yin, F.L.: Prediction of chaotic time series based on the recurrent predictor neural network. IEEE Trans. Sig. Process. 52(12), 3409–3416 (2004)MathSciNet CrossRef
  13.Karunasinghea, D.S.K., Liongb, S.Y.: Chaotic time series prediction with a global model: artificial neural network. J. Hydrol. 323(1–4), 92–105 (2006)CrossRef
  14.Takens, F.: Detecting Strange Attractors in Turbulence. Springer, Heidelberg (1981)CrossRef MATH
  15.Bennett, C.H.: Quantum information and computation. Phys. Today 48(10), 24–31 (1995)CrossRef
  16.Berman, G.P., Doolen, G.D., Mainieri, R., Tsifrinovich, V.I.: Introduction to Quantum Computers. World Scientific, River Edge (1998)CrossRef MATH
  17.Lorenz, E.N.: Deterministic nonperiodic flow. J. Atmos. Sci. 20(2), 130–141 (1963)CrossRef
  
• 作者单位：Taisei Ueguchi (19)
  Nobuyuki Matsui (19)
  Teijiro Isokawa (19)
  
  19. Graduate School of Engineering, University of Hyogo, 2167 Shosha, Himeji, Hyogo, 671-2280, Japan
  
• 丛书名：Neural Information Processing
• ISBN：978-3-319-46675-0
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9949

文摘

In recent years, quantum inspired neural networks have been applied to various practical problems since their proposal. Here we investigate whether our qubit neural network(QNN) leads to an advantage over the conventional (real-valued) neural network(NN) in the forecasting of chaotic time series. QNN is constructed from a set of qubit neuron, of which internal state is a coherent superposition of qubit states. In this paper, we evaluate the performance of QNN through a prediction of well-known Lorentz attractor, which produces chaotic time series by three dynamical systems. The experimental results show that QNN can forecast time series more precisely, compared with the conventional NN. In addition, we found that QNN outperforms the conventional NN by reconstructing the trajectories of Lorentz attractor.