一种量子神经网络模型学习算法及应用

A learning algorithm and its applications to the quantum neural network model

中文关键词  量子计算  量子神经元  量子神经网络  超线性收敛

英文关键词  quantum computing  quantum neuron  quantum neural network  super-linear convergence

中文摘要

      提出一种量子神经网络模型及学习算法. 首先基于生物神经元信息处理机制和量子计算原理构造出一种量子神经元, 该神经元由加权、聚合、活化、激励四部分组成. 然后由量子神经元构造出三层量子神经网络模型, 其输入和输出为实值向量, 权值和活性值为量子比特. 基于梯度下降法构造了该模型的超线性收敛学习算法. 通过模式识别和函数逼近两种仿真结果表明该模型及算法是有效的.

英文摘要

      A quantum neural network model and its learning algorithm are presented. According to the information processing mode of the biology neuron and the quantum computing theory, we first propose a quantum neuron model which includes weighting, aggregating, activating, and prompting. Secondly, the quantum neural network model based on quantum neuron is constructed in which both the input and the output are real vectors and both the linked weight and the activation value are qubits. Using gradient descent algorithm, we also propose a super-linearly convergent learning algorithm of the quantum neural network. Finally, the availability of the approach is illustrated by two application examples of pattern recognition and function approximation.