期刊
PHYSICAL REVIEW D
卷 105, 期 4, 页码 -出版社
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevD.105.043006
关键词
-
资金
- NIH Research Facility Improvement Grant [1G20RR030893-01]
- New York State Empire State Development, Division of Science Technology and Innovation (NYSTAR) [C090171]
- National Science Foundation [PHY-0757058, PHY-0823459, CCF-1740391, PHY-1911796]
- United States National Science Foundation (NSF)
- Science and Technology Facilities Council (STFC) of the United Kingdom
- Max-Planck-Society (MPS)
- State of Niedersachsen/Germany
- European Gravitational Observatory (EGO)
- French Centre National de Recherche Scientifique (CNRS)
- Italian Istituto Nazionale di Fisica Nucleare (INFN)
- Dutch Nikhef
- University of Florida
- Columbia University in the City of New York
- Alfred P. Sloan Foundation
This paper observes the relationship between deep learning and traditional matched filtering technique in the field of gravitational wave science. The author shows that matched filtering is equivalent to a specific neural network and proposes neural network architectures that outperform matched filtering. The theoretical findings are supported by experiments using real data and the paper suggests new perspectives on the role of deep learning in gravitational wave detection.
Gravitational wave science is a pioneering field with rapidly evolving data analysis methodology currently assimilating and inventing deep learning techniques. The bulk of the sophisticated flagship searches of the field rely on the time-tested matched filtering principle within their core. In this paper, we make a key observation on the relationship between the emerging deep learning and the traditional techniques: matched filtering is formally equivalent to a particular neural network. This means that a neural network can be constructed analytically to exactly implement matched filtering and can be further trained on data or boosted with additional complexity for improved performance. Moreover, we show that the proposed neural network architecture can outperform matched filtering, both with or without knowledge of a prior on the parameter distribution. When a prior is given, the proposed neural network can approach the statistically optimal performance. We also propose and investigate two different neural network architectures MNet-Shallow and MNet-Deep , both of which implement matched filtering at initialization and can be trained on data. MNet-Shallow has a simpler structure, while MNet-Deep is more flexible and can deal with a wider range of distributions. Our theoretical findings are corroborated by experiments using real LIGO data and synthetic injections, where our proposed methods significantly outperform matched filtering at false positive rates above 5 x 10(-3)%. The fundamental equivalence between matched filtering and neural networks allows us to define a complexity standard candle to characterize the relative complexity of the different approaches to gravitational wave signal searches in a common framework. Additionally, it also provides a glimpse of an intriguing symmetry that could provide clues on interpretability, namely how neural networks approach the problem of finding signals in overwhelming noise. Finally, our results suggest new perspectives on the role of deep learning in gravitational wave detection.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据