Abstract
Though neural networks have attracted much interest in the last two decades for their potential to describe brain function realistically, they have failed thus far to provide models that can be simulated in a reasonable time on computers, other than toy models. Quantum computing is a likely candidate for improving the computational efficiency of neural networks, since it has been very successful in doing so for a selected set of computational problems. In this framework, the Qubit neuron model, proposed by Matsui and Nishimura, has shown its promise in improving the efficiency. The simulations we have performed have shown that the Qubit model performs learning problems with significantly improved efficiency as compared to the classical model, and a classical model in which complex numbers are allowed as model parameters and as input. In this paper, we investigate what contributes to the efficiencies through 4-bit parity check problem known as a basic benchmark test. Our simulation suggests that the improved performance is due to the use of superposition of neural states and the use of the probability interpretation in the observation of the output states of the model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Deutsch, D., Jozsa, R.: Rapid solution of problems by quantum computation. Proc. of Royal Society of London series A 439, 553–558 (1992)
Shor, P.W.: Algorithm for quantum computation: discrete logarithms and factoring. In: Proc. the 35th Annual IEEE Symposium on Foundations of Computer Science, pp. 124–134 (1994)
Peruš, M.: Neuro-Quantum Parallelism in Brain-Mind and Computers. Informatica 20, 173–183 (1996)
Kak, S.C.: On quantum neural computing. Information Science 83, 143–163 (1995)
Matsui, N., Takai, M., Nishimura, H.: A network model based on qubit-like neuron corresponding to quantum circuit. IEICE J81-A(12), 1687–1692 (1998) (in Japanese). Electronics and Communications in Japan, Part 3 83(10), 67-73 (2000)
Kouda, N., Matsui, N., Nishimura, H.: A Multi-Layered Feed- Forward Network Based on Qubit Neuron Model. IEICE J81-A(12), 1687–1692 (2002) (in Japanese)
Kouda, N., Matsui, N., Nishimura, H.: Image Compression by Layered Quantum Neural Networks. Neural Processing Letters 16(1), 67–80 (2002)
Matsui, N., Kouda, N., Nishimura, H.: Neuralne Twork Based On Qbp And Its Performance. In: Proc. of International Joint Coference on Neural Networks 2000, vol. WB6-2 III, pp. 247–252 (2000)
Kouda, N., Matsui, N., Nishimura, H.: Learning Performance of Neuron Model based on Quantum Superposition. In: Proc. of the 2000 IEEE International Workshop on Robot and Human Interactive Communication, pp. 112–117 (2000)
Kouda, N., Matsui, N., Nishimura, H.: Control for Swing-up of an Inverted Pendulum using Qubit Neural Network. In: Proc. of SICE Annual Conference 2002 in Osaka, pp. 805–810 (2002)
Nitta, T.: An Extension of the Back-Propagation Algorithm to Complex Numbers. Neural Networks 10(8), 1391–1415 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kouda, N., Matsui, N., Nishimura, H., Peper, F. (2003). Qubit Neural Network and Its Efficiency. In: Palade, V., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2003. Lecture Notes in Computer Science(), vol 2774. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45226-3_42
Download citation
DOI: https://doi.org/10.1007/978-3-540-45226-3_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40804-8
Online ISBN: 978-3-540-45226-3
eBook Packages: Springer Book Archive