Qubit neural network and its learning efficiency

Neural networks have attracted much interest in the last two decades for their potential to realistically describe brain functions, but so far they have failed to provide models that can be simulated in a reasonable time on computers; rather they have been limited to toy models. Quantum computing is a possible candidate for improving the computational efficiency of neural networks. In this framework of quantum computing, the Qubit neuron model, proposed by Matsui and Nishimura, has shown a high efficiency in solving problems such as data compression. Simulations have shown that the Qubit model solves learning problems with significantly improved efficiency as compared to the classical model. In this paper, we confirm our previous results in further detail and investigate what contributes to the efficiency of our model through 4-bit and 6-bit parity check problems, which are known as basic benchmark tests. Our simulations suggest that the improved performance is due to the use of superposition of neural states and the use of probability interpretation in the observation of the output states of the model.

[1]  Ajit Narayanan,et al.  Quantum-inspired Neural Networks , 1995 .

[2]  Lov K. Grover,et al.  Quantum computation , 1999, Proceedings Twelfth International Conference on VLSI Design. (Cat. No.PR00013).

[3]  Barenco,et al.  Elementary gates for quantum computation. , 1995, Physical review. A, Atomic, molecular, and optical physics.

[4]  Peter W. Shor,et al.  Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer , 1995, SIAM Rev..

[5]  Nobuyuki Matsui,et al.  Learning performance of neuron model based on quantum superposition , 2000, Proceedings 9th IEEE International Workshop on Robot and Human Interactive Communication. IEEE RO-MAN 2000 (Cat. No.00TH8499).

[6]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[7]  Mitja Perus,et al.  Neuro-Quantum Parallelism in Brain-Mind and Computers , 1996, Informatica.

[8]  N. Matsui,et al.  Control for swing-up of an inverted pendulum using qubit neural network , 2002, Proceedings of the 41st SICE Annual Conference. SICE 2002..

[9]  Nobuyuki Matsui,et al.  A Multi-Layerd Feed-Forward Network Based on Qubit Neuron Model , 2002 .

[10]  Subhash C. Kak,et al.  On Quantum Neural Computing , 1995, Inf. Sci..

[11]  D. Deutsch,et al.  Rapid solution of problems by quantum computation , 1992, Proceedings of the Royal Society of London. Series A: Mathematical and Physical Sciences.

[12]  Tony R. Martinez,et al.  An Artificial Neuron with Quantum Mechanical Properties , 1997, ICANNGA.

[13]  N. Matsui,et al.  A network model based on qubitlike neuron corresponding to quantum circuit , 2000 .

[14]  Nobuyuki Matsui,et al.  Image Compression by Layered Quantum Neural Networks , 2002, Neural Processing Letters.

[15]  Elizabeth C. Behrman,et al.  A Quantum Dot Neural Network , 1996 .

[16]  Nobuyuki Matsui,et al.  Neural network based on QBP and its performance , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[17]  Tohru Nitta,et al.  An Extension of the Back-Propagation Algorithm to Complex Numbers , 1997, Neural Networks.