Show simple item record

dc.contributor.author
Gebhard, Timothy D.
dc.contributor.author
Kilbertus, Niki
dc.contributor.author
Harry, Ian
dc.contributor.author
Schölkopf, Bernhard
dc.date.accessioned
2019-10-15T09:58:06Z
dc.date.available
2019-10-15T02:38:31Z
dc.date.available
2019-10-15T09:58:06Z
dc.date.issued
2019-09-15
dc.identifier.issn
1550-7998
dc.identifier.issn
0556-2821
dc.identifier.issn
1550-2368
dc.identifier.other
10.1103/PhysRevD.100.063015
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/370468
dc.identifier.doi
10.3929/ethz-b-000370468
dc.description.abstract
In the last few years, machine learning techniques, in particular convolutional neural networks, have been investigated as a method to replace or complement traditional matched filtering techniques that are used to detect the gravitational-wave signature of merging black holes. However, to date, these methods have not yet been successfully applied to the analysis of long stretches of data recorded by the Advanced LIGO and Virgo gravitational-wave observatories. In this work, we critically examine the use of convolutional neural networks as a tool to search for merging black holes. We identify the strengths and limitations of this approach, highlight some common pitfalls in translating between machine learning and gravitational-wave astronomy, and discuss the interdisciplinary challenges. In particular, we explain in detail why convolutional neural networks alone cannot be used to claim a statistically significant gravitational-wave detection. However, we demonstrate how they can still be used to rapidly flag the times of potential signals in the data for a more detailed follow-up. Our convolutional neural network architecture as well as the proposed performance metrics are better suited for this task than a standard binary classifications scheme. A detailed evaluation of our approach on Advanced LIGO data demonstrates the potential of such systems as trigger generators. Finally, we sound a note of caution by constructing adversarial examples, which showcase interesting “failure modes” of our model, where inputs with no visible resemblance to real gravitational-wave signals are identified as such by the network with high confidence.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
American Physical Society (APS)
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.title
Convolutional neural networks: A magic bullet for gravitational-wave detection?
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
dc.date.published
2019-09-26
ethz.journal.title
Physical Review D
ethz.journal.volume
100
en_US
ethz.journal.issue
6
en_US
ethz.journal.abbreviated
Phys. rev. D.
ethz.pages.start
063015
en_US
ethz.size
19 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.identifier.scopus
ethz.publication.place
Ridge, NY
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::09664 - Schölkopf, Bernhard / Schölkopf, Bernhard
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::09664 - Schölkopf, Bernhard / Schölkopf, Bernhard
ethz.date.deposited
2019-10-15T02:38:39Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2019-10-15T09:58:18Z
ethz.rosetta.lastUpdated
2020-02-15T22:03:23Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Convolutional%20neural%20networks:%20A%20magic%20bullet%20for%20gravitational-wave%20detection?&rft.jtitle=Physical%20Review%20D&rft.date=2019-09-15&rft.volume=100&rft.issue=6&rft.spage=063015&rft.issn=1550-7998&0556-2821&1550-2368&rft.au=Gebhard,%20Timothy%20D.&Kilbertus,%20Niki&Harry,%20Ian&Sch%C3%B6lkopf,%20Bernhard&rft.genre=article&
 Search via SFX

Files in this item

Thumbnail

Publication type

Show simple item record