arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12906hep-phcs.AIcs.LGquant-ph
收藏

生成式可逆量子神经网络

Generative Invertible Quantum Neural Networks

Interdisciplinary Center for Scientific Computing, Universität Heidelberg(海德堡大学跨学科科学计算中心);Institute for Particle Physics Phenomenology, Department of Physics, Durham University(杜伦大学物理系粒子物理现象学研究所)

Armand Rousselot, Michael Spannowsky

AI总结:

提出一种用于量子可逆神经网络(QINN)的量子门算法,应用于LHC粒子对撞机数据,发现混合QINN能匹配更大规模纯经典INN的性能。

摘要:

可逆神经网络(INN)已成为模拟和生成高度复杂数据的成熟工具。我们提出了一种用于量子可逆神经网络(QINN)的量子门算法,并将其应用于Z玻色子衰变为轻子的喷注协同产生LHC数据,这是粒子对撞机精密测量的标准烛光过程。我们比较了QINN在不同损失函数和训练场景下的性能。对于此任务,我们发现混合QINN在学习和生成复杂数据时,匹配了规模显著更大的纯经典INN的性能。

英文摘要:

Invertible Neural Networks (INN) have become established tools for the simulation and generation of highly complex data. We propose a quantum-gate algorithm for a Quantum Invertible Neural Network (QINN) and apply it to the LHC data of jet-associated production of a Z-boson that decays into leptons, a standard candle process for particle collider precision measurements. We compare the QINN's performance for different loss functions and training scenarios. For this task, we find that a hybrid QINN matches the performance of a significantly larger purely classical INN in learning and generating complex data.

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。

↑