针对化学反应网络的贝叶斯验证(cs.CE)---用户7199428

我们展现了一个数据驱动的验证方法来决定一个给出的化学反应网（CRN）满足一个给定属性，在模态逻辑中以公式展现。我们的方法由3个阶段组成，基于数据产生的模型合成形式证明。首先，我们考虑到可能模型的参数集是基于一个已知的化学计量学，并且基于兴趣属性对它们进行分类。第二，我们利用贝叶斯推理去更新参数的概率的布，而这些参数包含于一个基于潜在CRN数据的参数模型，在第三也是最终阶段，我们将两步的结果组合起来计算，潜在的CRN有多大可能性满足给定属性。我们将这种新方法应用于个案研究，并且把它比做贝叶斯统计模型校验。

原文题目：Bayesian Verification of Chemical Reaction Networks

原文：We present a data-driven verification approach that determines whether or not a given chemical reaction network (CRN) satisfies a given property, expressed as a formula in a modal logic. Our approach consists of three phases, integrating formal verification over models with learning from data. First, we consider a parametric set of possible models based on a known stoichiometry and classify them against the property of interest. Secondly, we utilise Bayesian inference to update a probability distribution of the parameters within a parametric model with data gathered from the underlying CRN. In the third and final stage, we combine the results of both steps to compute the probability that the underlying CRN satisfies the given property. We apply the new approach to a case study and compare it to Bayesian statistical model checking.

原文作者：Gareth W. Molyneux, Viraj B. Wijesuriya, Alessandro Abate

原文地址：https://arxiv.org/abs/2004.11321