arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04459stat.MLcs.LG
收藏

贝叶斯物理信息神经网络用于不确定性感知的逆问题 (BPINN-IP)

Bayesian PINNs for uncertainty-aware inverse problems (BPINN-IP)

ISCT, Bures-sur-Yvette, France(法国ISCT);Institute of Digital Twin (IDT), EIT, Ningbo, China(中国宁波EIT数字孪生研究所);Dept. of Statistics, Central South University, Changcha, China(中国长沙中央南大学统计系)

Ali Mohammad-Djafari

AI总结:

本文提出了一种贝叶斯物理信息神经网络方法,用于解决具有不确定性的逆问题,通过引入先验知识和不确定性量化技术提升逆问题求解的鲁棒性。

摘要:

本文的主要贡献是开发了一种层次贝叶斯形式的物理信息神经网络(PINN)用于线性逆问题,称为BPINN-IP。所提出的方法扩展了PINN,以考虑对预期神经网络输出性质的先验知识及其权重。此外,由于可以访问后验概率分布,自然可以量化不确定性。同时,变分推断和蒙特卡洛滴答被用于为重建图像提供预测的均值和方差。考虑了一个应用于去卷积和超分辨率的例子,给出了不同实施步骤的细节,并展示了一些初步结果。

英文摘要:

The main contribution of this paper is to develop a hierarchical Bayesian formulation of PINNs for linear inverse problems, which is called BPINN-IP. The proposed methodology extends PINN to account for prior knowledge on the nature of the expected NN output, as well as its weights. Also, as we can have access to the posterior probability distributions, naturally uncertainties can be quantified. Also, variational inference and Monte Carlo dropout are employed to provide predictive means and variances for reconstructed images. Un example of applications to deconvolution and super-resolution is considered, details of the different steps of implementations are given, and some preliminary results are presented.

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。

↑