Quantum Neural Networks Learning Algorithm Based on a Global Search
Quantum Neural Networks Learning Algorithm Based on a Global Search
复制标题
基于全局搜索的量子神经网络学习算法
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
W. R. Oliveira
中科院分区：
文献类型：
--
作者：
F. M. P. Neto;Teresa B Ludermir;W. R. Oliveira
本文报道了一种基于量子搜索算法的量子神经网络训练算法的性能。该算法训练一个以次线性代价探索所有可能权值的QNN。训练成本理论上是O(√N/t)，作为可能的权重数量N的函数，t是可能的解的个数。初步实验结果表明，该算法总是收敛于已有的解，并且其均值和最大值几乎全部低于理论期望的最大值。该训练算法应用于分类问题。
This paper reports the performance of a novel training algorithm for quantum neural networks (QNN) using a variation of the quantum search algorithm. The proposed algorithm trains a QNN exploring all possible weights with a sublinear cost. The training cost is theoretically O(√N/t), as a function of the quantity N of possible weights and t is the number of possible solutions. Initial experimental results demonstrate that the algorithm always converges to existing solutions, in addition to having the mean and maximum values, almost in total, lower than the expected maximum amount, as theoretically expected. The training algorithm is applied to classification problems.