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 2509.02407cs.LGphysics.data-an
收藏

人工神经网络中的Fisher信息流

Fisher information flow in artificial neural networks

Institute for Theoretical Physics, Vienna University of Technology (TU Wien), A–1040 Vienna, Austria;School of Physics;Astronomy, University of Glasgow, Glasgow, G12 8QQ, United Kingdom;Faculty of Computer Science, Ruhr University Bochum, 44801 Bochum, Germany;Universit \'e Grenoble Alpes, CNRS, LIPhy, 38000 Grenoble, France

Maximilian Weimar, Lukas M. Rachbauer, Ilya Starshynov, Daniele Faccio, Linara Adilova, Dorian Bouchet, Stefan Rotter

AI总结:

本文提出监测人工神经网络中Fisher信息流的方法,发现最优估计对应最大信息传输,过拟合导致信息损失,从而提供无需验证集的训练停止准则,并在成像实验数据上验证其有效性。

摘要:

从测量数据中估计连续参数在许多物理学领域扮演着核心角色。理解和改进此类估计过程的一个关键工具是Fisher信息的概念,它量化了关于未知参数的信息如何通过物理系统传播,并决定了精度的最终极限。随着人工神经网络(ANNs)逐渐成为许多测量系统不可或缺的组成部分,理解它们如何在内部处理和传递与参数相关的信息至关重要。在此,我们提出了一种方法,用于监测执行参数估计任务的ANN中的Fisher信息流,从输入层追踪到输出层。我们表明,最优估计性能对应于Fisher信息的最大传输,而超过此点的训练会因过拟合而导致信息损失。这为网络训练提供了一个无模型的停止准则——消除了对单独验证数据集的需求。为了展示我们方法的实际相关性,我们将其应用于一个在成像实验数据上训练的网络,突出了其在现实物理环境中的有效性。

英文摘要:

The estimation of continuous parameters from measured data plays a central role in many fields of physics. A key tool in understanding and improving such estimation processes is the concept of Fisher information, which quantifies how information about unknown parameters propagates through a physical system and determines the ultimate limits of precision. With Artificial Neural Networks (ANNs) gradually becoming an integral part of many measurement systems, it is essential to understand how they process and transmit parameter-relevant information internally. Here, we present a method to monitor the flow of Fisher information through an ANN performing a parameter estimation task, tracking it from the input to the output layer. We show that optimal estimation performance corresponds to the maximal transmission of Fisher information, and that training beyond this point results in information loss due to overfitting. This provides a model-free stopping criterion for network training-eliminating the need for a separate validation dataset. To demonstrate the practical relevance of our approach, we apply it to a network trained on data from an imaging experiment, highlighting its effectiveness in a realistic physical setting.

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。

↑