Model and algorithm of quantum-inspired neural network with sequence input based on controlled rotation gates

To enhance the approximation and generalization ability of classical artificial neural network (ANN) by employing the principles of quantum computation, a quantum-inspired neuron based on controlled-rotation gate is proposed. In the proposed model, the discrete sequence input is represented by the qubits, which, as the control qubits of the controlled-rotation gate after being rotated by the quantum rotation gates, control the target qubit for rotation. The model output is described by the probability amplitude of state |1〉 in the target qubit. Then a quantum-inspired neural network with sequence input (QNNSI) is designed by employing the quantum-inspired neurons to the hidden layer and the classical neurons to the output layer. An algorithm of QNNSI is derived by employing the Levenberg–Marquardt algorithm. Experimental results of some benchmark problems show that, under a certain condition, the QNNSI is obviously superior to the ANN.

[1]  Richard Lippmann,et al.  Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[2]  Martin T. Hagan,et al.  Neural network design , 1995 .

[3]  Sung-Kwun Oh,et al.  Polynomial-based radial basis function neural networks (P-RBF NNs) and their application to pattern classification , 2010, Applied Intelligence.

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

[5]  Colin P. Williams,et al.  Quantum Neural Nets , 1998 .

[6]  Liao Shiyong,et al.  Learning algorithm and application of quantum BP neural networks based on universal quantum gates , 2008 .

[7]  Ah Chung Tsoi,et al.  Locally recurrent globally feedforward networks: a critical review of architectures , 1994, IEEE Trans. Neural Networks.

[8]  D Kleinfeld,et al.  Sequential state generation by model neural networks. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Mohammad Taghi Hamidi Beheshti,et al.  A local linear radial basis function neural network for financial time-series forecasting , 2010, Applied Intelligence.

[10]  Chris Christodoulou,et al.  Artificial neural networks for earthquake prediction using time series magnitude data or Seismic Electric Signals , 2011, Expert Syst. Appl..

[11]  Fariel Shafee,et al.  Neural networks with quantum gated nodes , 2002, Eng. Appl. Artif. Intell..

[12]  Ángel García-Crespo,et al.  Dealing with limited data in ballistic impact scenarios: an empirical comparison of different neural network approaches , 2011, Applied Intelligence.

[13]  Ángel García-Crespo,et al.  An optimization methodology for machine learning strategies and regression problems in ballistic impact scenarios , 2012, Applied Intelligence.

[14]  O. Mangasarian,et al.  Robust linear programming discrimination of two linearly inseparable sets , 1992 .

[15]  Teresa Bernarda Ludermir,et al.  Classical and superposed learning for quantum weightless neural networks , 2012, Neurocomputing.

[16]  M. Altaisky.  Quantum neural network , 2001 .

[17]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[18]  Michiharu Maeda,et al.  Qubit neuron according to quantum circuit for XOR problem , 2007, Appl. Math. Comput..

[19]  Yasser F. Hassan,et al.  Rough sets for adapting wavelet neural networks as a new classifier system , 2011, Applied Intelligence.

[20]  Kyoung-jae Kim,et al.  Simultaneous optimization of artificial neural networks for financial forecasting , 2012, Applied Intelligence.

[21]  Witold Pedrycz,et al.  A new selective neural network ensemble with negative correlation , 2012, Applied Intelligence.

[22]  Sanjay Gupta,et al.  Quantum Neural Networks , 2001, J. Comput. Syst. Sci..

[23]  Gopathy Purushothaman,et al.  Quantum neural networks (QNNs): inherently fuzzy feedforward neural networks , 1997, IEEE Trans. Neural Networks.