The quantum perceptron, the variational circuit, and the Grover algorithm have been proposed as promising components for quantum machine learning. This paper presents a new quantum perceptron that combines the quantum variational circuit and the Grover algorithm. However, this does not guarantee that this quantum variational perceptron with Grover's algorithm (QVPG) will have any advantage over its quantum variational (QVP) and classical counterparts. Here, we examine the performance of QVP and QVP-G by computing their loss function and analyzing their accuracy on the classification task, then comparing these two quantum models to the classical perceptron (CP). The results show that our two quantum models are more efficient than CP, and our novel suggested model QVP-G outperforms the QVP, demonstrating that the Grover can be applied to the classification task and even makes the model more accurate, besides the unstructured search problems.

翻译：量子感知机、变分电路以及Grover算法已被提出作为量子机器学习中具有前景的组件。本文提出一种结合量子变分电路与Grover算法的新型量子感知机。然而，这并不能保证基于Grover算法的量子变分感知机（QVPG）相较于其量子变分感知机（QVP）及经典感知机具有任何优势。本文通过计算损失函数并分析分类任务中的准确率，检验了QVP和QVPG的性能，并将这两种量子模型与经典感知机（CP）进行了比较。结果表明，我们的两种量子模型效率均高于CP，并且我们新提出的QVPG模型优于QVP。这证明除非结构搜索问题外，Grover算法也可应用于分类任务，甚至能提升模型的准确率。