OJAppS  Vol.5 No.6 , June 2015
Quantum-Inspired Neural Network with Sequence Input
Abstract: To enhance the approximation and generalization ability of artificial neural network (ANN) by employing the principles of quantum rotation gate and controlled-not gate, a quantum-inspired neuron with sequence input is proposed. In the proposed model, the discrete sequence input is represented by the qubits, which, as the control qubits of the controlled-not gate after being rotated by the quantum rotation gates, control the target qubit for reverse. The model output is described by the probability amplitude of state in the target qubit. Then a quantum-inspired neural network with sequence input (QNNSI) is designed by employing the sequence input-based quantum-inspired neurons to the hidden layer and the classical neurons to the output layer, and a learning algorithm is derived by employing the Levenberg-Marquardt algorithm. Simulation results of benchmark problem show that, under a certain condition, the QNNSI is obviously superior to the ANN.
Cite this paper: Li, Z. and Li, P. (2015) Quantum-Inspired Neural Network with Sequence Input. Open Journal of Applied Sciences, 5, 259-269. doi: 10.4236/ojapps.2015.56027.

[1]   Tsoi, A.C. and Back, A.D. (1994) Locally Recurrent Globally Feed Forward Network: A Critical Review of Architectures. IEEE Transactions on Neural Network, 7, 229-239.

[2]   Kleinfeld, A.D. (1986) Sequential State Generation by Model Neural Network. Proceedings of the National Academy of Sciences USA, 83, 9469-9473.

[3]   Waibel, A., Hanazawa, A. and Hinton, A. (1989) Phoneme Recognition Using Time-Delay Neural Network. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37, 328-339.

[4]   Lippmann, R.P. (1989) Review of Neural Network for Speech Recognition. Neural Computation, 1, 1-38.

[5]   Maria, M., Marios, A. and Chris, C. (2011) Artificial Neural Network for Earthquake Prediction Using Time Series Magnitude Data or Seismic Electric Signals. Expert Systems with Applications, 38, 15032-15039.

[6]   Kak, S. (1995) On Quantum Neural Computing. Information Sciences, 83, 143-160.

[7]   Gopathy, P. and Nicolaos, B.K. (1997) Quantum Neural Network (QNN's): Inherently Fuzzy Feed forward Neural Network. IEEE Transactions on Neural Network, 8, 679-693.

[8]   Zak, M. and Williams, C.P. (1998) Quantum Neural Nets. International Journal of Theoretical Physics, 3, 651-684.

[9]   Maeda, M., Suenaga, M. and Miyajima, H. (2007) Qubit Neuron According to Quantum Circuit for XOR Problem. Applied Mathematics and Computation, 185, 1015-1025.

[10]   Gupta, S. and Zia, R.K. (2001) Quantum Neural Network. Journal of Computer and System Sciences, 63, 355-383.

[11]   Shafee, F. (2007) Neural Network with Quantum Gated Nodes. Engineering Applications of Artificial Intelligence, 20, 429-437.

[12]   Li, P.C., Song, K.P. and Yang, E.L. (2010) Model and Algorithm of Neural Network with Quantum Gated Nodes. Neural Network World, 11, 189-206.

[13]   Adenilton, J., Wilson, R. and Teresa, B. (2012) Classical and Superposed Learning for Quantum Weightless Neural Network. Neurocomputing, 75, 52-60.

[14]   Israel, G.C., Angel, G.C. and Belen, R.M. (2012) Dealing with Limited Data in Ballistic Impact Scenarios: An Empirical Comparison of Different Neural Network Approaches. Applied Intelligence, 35, 89-109.

[15]   Israel, G.C., Angel, G.C. and Belen, R.M. (2013) An Optimization Methodology for Machine Learning Strategies and Regression Problems in Ballistic Impact Scenarios. Applied Intelligence, 36, 424-441.

[16]   Martin, T.H., Howard, B.D. and Mark, H.B. (1996) Neural Network Design. PWS Publishing Company, Boston, 391- 399.

[17]   Mackey, M.C. and Glass, L. (1977) Oscillation and Chaos in Physiological Control System. Science, 197, 287-289.