arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.01288astro-ph.IMastro-ph.COastro-ph.GAcs.LGeess.SPphysics.data-an
收藏

如何量化场或纹理?散射变换指南

How to quantify fields or textures? A guide to the scattering transform

The Johns Hopkins University(约翰斯·霍普金斯大学);Ecole Normale Supérieure(巴黎高等师范学院)

Sihao Cheng, Brice Ménard

摘要:

从随机场或纹理中提取信息是科学中普遍存在的任务,从探索性数据分析到分类和参数估计。从物理学到生物学,它往往是通过功率谱分析来完成的,功率谱分析通常过于有限,或者使用卷积神经网络(CNN),这需要大量的训练集并且缺乏可解释性。在本文中,我们提倡使用散射变换(Mallat 2012),这是一种强大的统计方法,它借用了CNN的数学思想,但不需要任何训练,并且是可解释的。我们发现,它提供了一个相对紧凑的汇总统计与直观的解释,并进行了广泛的科学应用中的大部分相关信息。我们提出了一个非技术性的介绍,这个估计,我们认为,它可以有利于数据分析,比较模型和参数推断在许多科学领域。有趣的是,理解散射变换的核心运算可以让人们破译CNN内部工作的许多关键方面。

英文摘要:

Extracting information from stochastic fields or textures is a ubiquitous task in science, from exploratory data analysis to classification and parameter estimation. From physics to biology, it tends to be done either through a power spectrum analysis, which is often too limited, or the use of convolutional neural networks (CNNs), which require large training sets and lack interpretability. In this paper, we advocate for the use of the scattering transform (Mallat 2012), a powerful statistic which borrows mathematical ideas from CNNs but does not require any training, and is interpretable. We show that it provides a relatively compact set of summary statistics with visual interpretation and which carries most of the relevant information in a wide range of scientific applications. We present a non-technical introduction to this estimator and we argue that it can benefit data analysis, comparison to models and parameter inference in many fields of science. Interestingly, understanding the core operations of the scattering transform allows one to decipher many key aspects of the inner workings of CNNs.

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。

↑