Author(s)

Ziyang Li^1*, Panchi Li²

¹School of Earth Science, Northeast Petroleum University, Daqing, China.
²School of Computer and Information Technology, Northeast Petroleum University, Daqing, China.

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.

Quantum Rotation Gate, Multi-Qubits Controller-Not Gate, Quantum-Inspired Neuron, Quantum-Inspired Neural Network

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.