arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.00378quant-phcs.LG
收藏

量子循环神经网络的快速训练

Rapid training of quantum recurrent neural networks

University of Warsaw(华沙大学);European Space Agency(欧洲空间局)

Michał Siemaszko, Adam Buraczewski, Bertrand Le Saux, Magdalena Stobińska

AI总结:

针对时间序列预测中经典RNN训练复杂且耗能高的问题,提出基于连续变量量子计算范式的CV-QRNN,证明其在更少epoch内收敛且在少量参数下损失更低,可由量子光子硬件实现。

摘要:

时间序列预测对人类在各个领域的活动至关重要。处理该任务的一种常见方法是利用循环神经网络(RNNs)。然而,尽管其预测相当准确,其学习过程却很复杂,因此耗时且耗能。在此,我们提出通过在其中引入连续变量量子资源来扩展 RRNs 的概念,并使用量子增强的 RNN 来克服这些障碍。连续变量量子 RNN(CV-QRNN)的设计根植于连续变量量子计算范式。通过进行广泛的数值模拟,我们证明该量子网络能够学习多种类型时间数据的时间依赖性,并且比经典网络在更少的 epoch 内收敛到最优权重。此外,对于少量可训练参数,它能实现比其经典对应物更低的损失。CV-QRNN 可使用市售的量子光子硬件实现。

英文摘要:

Time series prediction is essential for human activities in diverse areas. A common approach to this task is to harness Recurrent Neural Networks (RNNs). However, while their predictions are quite accurate, their learning process is complex and, thus, time and energy consuming. Here, we propose to extend the concept of RRNs by including continuous-variable quantum resources in it, and to use a quantum-enhanced RNN to overcome these obstacles. The design of the Continuous-Variable Quantum RNN (CV-QRNN) is rooted in the continuous-variable quantum computing paradigm. By performing extensive numerical simulations, we demonstrate that the quantum network is capable of learning-time dependence of several types of temporal data, and that it converges to the optimal weights in fewer epochs than a classical network. Furthermore, for a small number of trainable parameters, it can achieve lower losses than its classical counterpart. CV-QRNN can be implemented using commercially available quantum-photonic hardware.

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。

↑