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 2211.01441quant-phcs.AIcs.GT
收藏

用于量子机器学习的eXplainable AI

eXplainable AI for Quantum Machine Learning

d-fine GmbH(d-fine有限公司);d-fine AG(d-fine股份公司)

Patrick Steinmüller, Tobias Schulz, Ferdinand Graf, Daniel Herr

摘要:

参数化量子线路(PQC)为机器学习(ML)提供了一种新的方法。然而,从计算的角度来看,它们对现有的可解释人工智能(xAI)方法提出了挑战。一方面,对量子线路的测量引入了影响这些方法收敛的概率误差。另一方面,量子线路的相空间随着量子比特的数量呈指数级扩展,这使得在多项式时间内执行xAI方法的工作变得复杂。在本文中,我们将讨论已建立的xAI方法的性能,如基线SHAP和集成的参数。利用PQC的内部机制,我们研究如何加快其计算。

英文摘要:

Parametrized Quantum Circuits (PQCs) enable a novel method for machine learning (ML). However, from a computational point of view they present a challenge to existing eXplainable AI (xAI) methods. On the one hand, measurements on quantum circuits introduce probabilistic errors which impact the convergence of these methods. On the other hand, the phase space of a quantum circuit expands exponentially with the number of qubits, complicating efforts to execute xAI methods in polynomial time. In this paper we will discuss the performance of established xAI methods, such as Baseline SHAP and Integrated Gradients. Using the internal mechanics of PQCs we study ways to speed up their computation.

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。

↑