用于深度学习的基于测量的量子卷积神经网络
Measurement-based quantum convolutional neural network for deep learning
AI总结:
针对现有量子卷积神经网络需精确动力学控制、大规模实现困难的问题,提出基于测量的簇态实现方案,通过调整量子比特投影基训练,避免复杂控制,实现更快收敛,为量子深度学习实际应用提供可行路径。
摘要:
近年来,量子卷积神经网络(QCNNs)被提出,利用量子计算的能力实现了比经典卷积神经网络更快的训练速度。然而,这种深度学习框架同样依赖多层处理来捕获数据表征,这就要求实现精确的动力学控制。在量子计算的当前发展阶段,大规模实现这种程度的控制仍然颇具挑战。本文中,我们提出了一种利用簇态实现QCNNs的替代方法。该方法的训练过程涉及调整簇态中每个量子比特的投影基,而非调节深度量子电路中各层算符的参数,因此整个系统无需复杂控制,更易保持稳定。我们借助基于测量的量子计算技术,给出了通用QCNNs的精确簇态解。随后我们提供的数值证据表明,通过测量簇态既可以学习量子数据也可以学习经典数据,且观测到该方法具有更快的收敛速度。我们在学习示例中采用的簇态仅为方格簇态,其大规模实现已有相关报道。这表明我们的方法有望推动量子深度学习的实际应用落地。
英文摘要:
Recently, quantum convolutional neural networks (QCNNs) are proposed, harnessing the power of quantum computing for faster training compared to the classical counterparts. However, this framework for deep learning also relies on multiple processing layers to capture the representation of data, which necessitates precise dynamical control. Given the current stage of quantum computing, achieving this level of control at a large scale remains challenging. Here, we propose an alternate approach to implementing QCNNs by utilizing cluster states. The training process of the method involves tuning the projection basis of each qubit in cluster states, rather than adjusting the parameters of layers of operators in deep quantum circuits. Hence, the whole system is easier to stabilize by avoiding the complex controls. Leveraging techniques in measurement-based quantum computing, we present an exact cluster state solution to general QCNNs. Followingly, we provide numerical evidence that both quantum and classical data can be learned by measuring cluster states, and a faster convergence of the method is observed. The cluster states we consider in our learning examples are merely square-lattice cluster states, whose implementation at large scale have been reported recently. It indicates that our method has the potential for realizing the advance of quantum deep learning for practical uses.
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。