一种基于LM的量子神经网络训练算法  

LM Based Training Algorithm for Quantum Neural Networks

作　　者：张翼鹏[1] 陈亮[1] 郝欢[1] 

机构地区：[1]解放军理工大学通信工程学院,南京210007

出　　处：《计算机科学》2013年第9期221-224,共4页Computer Science

基　　金：国家自然科学基金项目(61072042)资助

摘　　要：针对量子神经网络的训练结果易陷入局部极小值的问题,将Levenberg-Marquardt(LM)算法引入到原训练算法中,从而提高网络收敛速度与训练效果。并通过改进原训练算法的迭代步骤,解决训练过程中网络权值与量子间隔不同的目标函数相互冲突引起的输出均方误差和波动的问题。实验结果表明,相比原训练算法,引入LM后的训练算法可以大幅减少迭代次数,显著降低网络收敛值,提高量子神经网络的分类效果。Aiming at the question that the result trained by quantum neural networks is easy to fall into the local least value, the Levenberg-Marquardt algorithm was introduced into the original training algorithm to increase the training speed and improve the performance of the network. In addition, the conflict between different objective functions used for the training synaptic weights and quantum intervals can cause mean square error fluctuates. In order to solve this problem,the iteration order of the original training algorithm was adjusted. The experimental results show that, com-pared with the original training algorithm, the algorithm using LM can significantly reduce the number of iterations, sig-nificantly decrease the mean square error when the network convergenees, and improve the classification results of quan-tum neural network.

关 键 词：量子神经网络 LEVENBERG-MARQUARDT算法 最速下降 量子间隔 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]