期刊名称：International Journal of Computer and Information Technology
印刷版ISSN：2279-0764
出版年度：2015
卷号：4
期号：3
出版社：International Journal of Computer and Information Technology
摘要：On the basis of analyzing the principles of the quantum rotation gates and quantum controlled-NOT gates, a novel quantum neural networks model is proposed in our paper. In this model, the input information is expressed by the qubits, which, as the control qubits after rotated by the rotation gate, control the qubits in the hidden layer to reverse. The qubits in the hidden layer, as the control qubits after rotated by the rotation gate, control the qubits in the output layer to reverse. The networks output is described by the probability amplitude of state . 1 | in the output layer. The learning algorithm is derived and discussed based on the gradient descent algorithm. It has been shown in two application examples of pattern recognition and function approximation that this new quantum neural network model is superior to the standard BP networks with regard to their convergence rate, number of iterations, approximation ability, and robustness
