arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00653quant-phcs.LG
收藏

相干前馈量子神经网络

Coherent Feed Forward Quantum Neural Network

National Research Council of Canada(加拿大国家研究委员会);University of Ottawa(渥太华大学);University of Calgary(卡尔加里大学)

Utkarsh Singh, Aaron Z. Goldberg, Khabat Heshami

AI总结:

针对现有量子神经网络线路深、资源需求高、与经典前馈网络结构差异大的问题,提出无中间测量的相干前馈量子神经网络,在更少量子资源下于多个基准数据集取得更优性能。

摘要:

聚焦于量子神经网络(QNN)的量子机器学习仍是一个远未被充分探索的研究领域。当前的QNN模型主要在拟设(ansatz)或量子特征映射上采用变分线路,通常需要多层纠缠层。这种方法不仅会使线路的计算成本升高到超出近期量子设备的实际可行范围,而且由于其与典型前馈神经网络(FFNN)的结构存在差异,将这些模型标记为神经网络具有误导性。此外,这些模型的线路深度和量子比特需求随数据特征数量的扩展性很差,给现实世界的机器学习任务带来了效率挑战。我们提出了一种真正的QNN模型,它在可适配的中间层和节点方面与传统FFNN的多功能性无缝契合,且不存在中间测量,因此整个模型是相干的。该模型的突出优势在于其线路深度更浅、所需的C-NOT门数量更少,性能优于主流QNN模型。此外,我们模型中的量子比特数量不受数据特征数量的影响。我们在多个基准数据集(例如威斯康星州乳腺癌诊断数据集和信用卡欺诈检测数据集)上测试了所提出的模型。我们将模型的结果与现有QNN方法进行了比较,以展示我们的方法即使在量子资源需求降低的情况下仍具有更优的效能。我们的模型为量子神经网络应用于实际相关的机器学习问题铺平了道路。

英文摘要:

Quantum machine learning, focusing on quantum neural networks (QNNs), remains a vastly uncharted field of study. Current QNN models primarily employ variational circuits on an ansatz or a quantum feature map, often requiring multiple entanglement layers. This methodology not only increases the computational cost of the circuit beyond what is practical on near-term quantum devices but also misleadingly labels these models as neural networks, given their divergence from the structure of a typical feed-forward neural network (FFNN). Moreover, the circuit depth and qubit needs of these models scale poorly with the number of data features, resulting in an efficiency challenge for real-world machine-learning tasks. We introduce a bona fide QNN model, which seamlessly aligns with the versatility of a traditional FFNN in terms of its adaptable intermediate layers and nodes, absent from intermediate measurements such that our entire model is coherent. This model stands out with its reduced circuit depth and number of requisite C-NOT gates to outperform prevailing QNN models. Furthermore, the qubit count in our model remains unaffected by the data's feature quantity. We test our proposed model on various benchmarking datasets such as the diagnostic breast cancer (Wisconsin) and credit card fraud detection datasets. We compare the outcomes of our model with the existing QNN methods to showcase the advantageous efficacy of our approach, even with a reduced requirement on quantum resources. Our model paves the way for application of quantum neural networks to real relevant machine learning problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑