匹配点集与量子电路学习
Matching Point Sets with Quantum Circuit Learning
摘要:
在这项工作中,我们提出了一个参数化的量子电路学习方法的点集匹配问题。与以前的基于退火的方法相比,我们提出了一个基于量子电路的框架,其参数通过降低基于内核的损失函数的梯度来优化。我们将形状匹配问题转化为一个分布学习任务,即学习最优变换参数的分布。我们表明,该框架是能够找到多个对称形状的最佳解决方案,是更准确,可扩展性和鲁棒性比以前的退火为基础的方法。代码、数据和预先训练的权重可在项目页面上获得:\href{https://hansen7.github.io/qKC}{https://hansen7.github.io/qKC}
英文摘要:
In this work, we propose a parameterised quantum circuit learning approach to point set matching problem. In contrast to previous annealing-based methods, we propose a quantum circuit-based framework whose parameters are optimised via descending the gradients w.r.t a kernel-based loss function. We formulate the shape matching problem into a distribution learning task; that is, to learn the distribution of the optimal transformation parameters. We show that this framework is able to find multiple optimal solutions for symmetric shapes and is more accurate, scalable and robust than the previous annealing-based method. Code, data and pre-trained weights are available at the project page: \href{https://hansen7.github.io/qKC}{https://hansen7.github.io/qKC}
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。