量子过程神经网络模型算法及应用

为提高过程神经网络的逼近和泛化能力, 从研究过程神经元信息处理的量子计算实现机理入手, 提出基于量子旋转门及多位受控非门的物理意义构造量子过程神经元的新思想. 将离散化后的过程式输入信息作为受控非门的控制位, 经过量子旋转门作用后控制目标量子位的状态, 以目标量子位处于状态|1>概率幅作为量子过程神经元的输出. 以量子过程神经元为隐层, 普通神经元为输出层, 可构成量子过程神经网络. 基于量子计算机理推导了该模型的学习算法. 将该模型用于太阳黑子数年均值预测, 应用结果表明, 所提方法与普通过程神经网络相比, 预测精度有所提高, 对于复杂预测问题具有一定理论意义和实用价值.

Quantum process neural networks model algorithm and applications

To enhance the approximation and generalization ability of process neural networks (PNNs), by studying the quantum implementation mechanism of information processing of process neuron, a new idea of designing quantum process neuron is proposed in this paper, based on the quantum rotation gates and the quantum controlled-non gates. In the proposed approach, the discrete process inputs are expressed by the qubits, which, as the control qubits of controlled-non gates after being rotated by the quantum rotation gates, control the target qubits to reverse. The model outputs are described by the probability amplitude of state |1> in the target qubits. Then the quantum process neural networks (QPNNs) are designed by the quantum process neurons for the hidden layer and the normal neurons for the output layer. The algorithm of QPNN is derived through the quantum computing. The proposed approach is utilized to predict the smoothed yearly mean sunspot numbers, and the results indicate that the QPNN has higher prediction accuracy than the normal PNN, thus it has a certain theoretical meaning and practical value for the complex prediction.