Deep learning as a parton shower View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-12

AUTHORS

J. W. Monk

ABSTRACT

We make the connection between certain deep learning architectures and the renormalisation group explicit in the context of QCD by using a deep learning network to construct a toy parton shower model. The model aims to describe proton-proton collisions at the Large Hadron Collider. A convolutional autoencoder learns a set of kernels that efficiently encode the behaviour of fully showered QCD collision events. The network is structured recursively so as to ensure self-similarity, and the number of trained network parameters is low. Randomness is introduced via a novel custom masking layer, which also preserves existing parton splittings by using layer-skipping connections. By applying a shower merging procedure, the network can be evaluated on unshowered events produced by a matrix element calculation. The trained network behaves as a parton shower that qualitatively reproduces jet-based observables. More... »

PAGES

21

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/jhep12(2018)021

DOI

http://dx.doi.org/10.1007/jhep12(2018)021

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1110668203


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/17", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology and Cognitive Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Copenhagen", 
          "id": "https://www.grid.ac/institutes/grid.5254.6", 
          "name": [
            "Niels Bohr Institute, University of Copenhagen, Blegdamsvej, Copenhagen, Denmark"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Monk", 
        "givenName": "J. W.", 
        "id": "sg:person.010300415037.23", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010300415037.23"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1088/1126-6708/2009/05/053", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002941310", 
          "https://doi.org/10.1088/1126-6708/2009/05/053"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1088/1126-6708/2009/05/053", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002941310", 
          "https://doi.org/10.1088/1126-6708/2009/05/053"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1103/physrevd.48.3160", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006547860"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1103/physrevd.48.3160", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006547860"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0550-3213(84)90463-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006667108"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0550-3213(84)90463-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006667108"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1140/epjc/s10052-012-1896-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009624676", 
          "https://doi.org/10.1140/epjc/s10052-012-1896-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cpc.2013.05.021", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1011366723"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1088/1126-6708/2009/11/038", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019772541", 
          "https://doi.org/10.1088/1126-6708/2009/11/038"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1088/1126-6708/2009/11/038", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019772541", 
          "https://doi.org/10.1088/1126-6708/2009/11/038"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1088/1126-6708/2008/03/038", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031316682", 
          "https://doi.org/10.1088/1126-6708/2008/03/038"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-2789(90)90175-o", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034195333"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-2789(90)90175-o", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034195333"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1103/physrevd.87.054012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035956013"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1103/physrevd.87.054012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035956013"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-2789(84)90245-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039676522"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-2789(84)90245-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039676522"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0550-3213(88)90089-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039919508"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0550-3213(88)90089-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039919508"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/jhep07(2016)069", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045717527", 
          "https://doi.org/10.1007/jhep07(2016)069"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/jhep07(2016)069", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045717527", 
          "https://doi.org/10.1007/jhep07(2016)069"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1140/epjc/s10052-008-0798-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047392024", 
          "https://doi.org/10.1140/epjc/s10052-008-0798-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1088/1126-6708/2008/12/039", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050931083", 
          "https://doi.org/10.1088/1126-6708/2008/12/039"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/jhep01(2017)110", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1074216551", 
          "https://doi.org/10.1007/jhep01(2017)110"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/jhep01(2017)110", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1074216551", 
          "https://doi.org/10.1007/jhep01(2017)110"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s41781-017-0004-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091994251", 
          "https://doi.org/10.1007/s41781-017-0004-6"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-12", 
    "datePublishedReg": "2018-12-01", 
    "description": "We make the connection between certain deep learning architectures and the renormalisation group explicit in the context of QCD by using a deep learning network to construct a toy parton shower model. The model aims to describe proton-proton collisions at the Large Hadron Collider. A convolutional autoencoder learns a set of kernels that efficiently encode the behaviour of fully showered QCD collision events. The network is structured recursively so as to ensure self-similarity, and the number of trained network parameters is low. Randomness is introduced via a novel custom masking layer, which also preserves existing parton splittings by using layer-skipping connections. By applying a shower merging procedure, the network can be evaluated on unshowered events produced by a matrix element calculation. The trained network behaves as a parton shower that qualitatively reproduces jet-based observables.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/jhep12(2018)021", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1052482", 
        "issn": [
          "1126-6708", 
          "1029-8479"
        ], 
        "name": "Journal of High Energy Physics", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "12", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "2018"
      }
    ], 
    "name": "Deep learning as a parton shower", 
    "pagination": "21", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "29d170a11841a33b7ad10f57da64683220625b225452a104b5a896114b787eb3"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/jhep12(2018)021"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1110668203"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/jhep12(2018)021", 
      "https://app.dimensions.ai/details/publication/pub.1110668203"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T08:24", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000296_0000000296/records_57243_00000000.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2FJHEP12%282018%29021"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/jhep12(2018)021'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/jhep12(2018)021'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/jhep12(2018)021'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/jhep12(2018)021'


 

This table displays all metadata directly associated to this object as RDF triples.

118 TRIPLES      21 PREDICATES      43 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/jhep12(2018)021 schema:about anzsrc-for:17
2 anzsrc-for:1701
3 schema:author N7afe74d4a87c413bb63074fdf37137e5
4 schema:citation sg:pub.10.1007/jhep01(2017)110
5 sg:pub.10.1007/jhep07(2016)069
6 sg:pub.10.1007/s41781-017-0004-6
7 sg:pub.10.1088/1126-6708/2008/03/038
8 sg:pub.10.1088/1126-6708/2008/12/039
9 sg:pub.10.1088/1126-6708/2009/05/053
10 sg:pub.10.1088/1126-6708/2009/11/038
11 sg:pub.10.1140/epjc/s10052-008-0798-9
12 sg:pub.10.1140/epjc/s10052-012-1896-2
13 https://doi.org/10.1016/0167-2789(84)90245-8
14 https://doi.org/10.1016/0167-2789(90)90175-o
15 https://doi.org/10.1016/0550-3213(84)90463-2
16 https://doi.org/10.1016/0550-3213(88)90089-2
17 https://doi.org/10.1016/j.cpc.2013.05.021
18 https://doi.org/10.1103/physrevd.48.3160
19 https://doi.org/10.1103/physrevd.87.054012
20 schema:datePublished 2018-12
21 schema:datePublishedReg 2018-12-01
22 schema:description We make the connection between certain deep learning architectures and the renormalisation group explicit in the context of QCD by using a deep learning network to construct a toy parton shower model. The model aims to describe proton-proton collisions at the Large Hadron Collider. A convolutional autoencoder learns a set of kernels that efficiently encode the behaviour of fully showered QCD collision events. The network is structured recursively so as to ensure self-similarity, and the number of trained network parameters is low. Randomness is introduced via a novel custom masking layer, which also preserves existing parton splittings by using layer-skipping connections. By applying a shower merging procedure, the network can be evaluated on unshowered events produced by a matrix element calculation. The trained network behaves as a parton shower that qualitatively reproduces jet-based observables.
23 schema:genre research_article
24 schema:inLanguage en
25 schema:isAccessibleForFree true
26 schema:isPartOf N2f7a5d47839c4404ace5adccf8b5fbce
27 Naa80bbb3ff0544a5a29172b3dae895ae
28 sg:journal.1052482
29 schema:name Deep learning as a parton shower
30 schema:pagination 21
31 schema:productId N161c4ce48443403698ef56dcf8ef42f0
32 N55c87f92e3434b60bef95b5ef6e1e450
33 Ndb567358fd574e6780e5b73e53ddd6c9
34 schema:sameAs https://app.dimensions.ai/details/publication/pub.1110668203
35 https://doi.org/10.1007/jhep12(2018)021
36 schema:sdDatePublished 2019-04-11T08:24
37 schema:sdLicense https://scigraph.springernature.com/explorer/license/
38 schema:sdPublisher N4bbba6c8ef01481b8cf8072ab8b0f1b2
39 schema:url https://link.springer.com/10.1007%2FJHEP12%282018%29021
40 sgo:license sg:explorer/license/
41 sgo:sdDataset articles
42 rdf:type schema:ScholarlyArticle
43 N161c4ce48443403698ef56dcf8ef42f0 schema:name doi
44 schema:value 10.1007/jhep12(2018)021
45 rdf:type schema:PropertyValue
46 N2f7a5d47839c4404ace5adccf8b5fbce schema:issueNumber 12
47 rdf:type schema:PublicationIssue
48 N4bbba6c8ef01481b8cf8072ab8b0f1b2 schema:name Springer Nature - SN SciGraph project
49 rdf:type schema:Organization
50 N55c87f92e3434b60bef95b5ef6e1e450 schema:name readcube_id
51 schema:value 29d170a11841a33b7ad10f57da64683220625b225452a104b5a896114b787eb3
52 rdf:type schema:PropertyValue
53 N7afe74d4a87c413bb63074fdf37137e5 rdf:first sg:person.010300415037.23
54 rdf:rest rdf:nil
55 Naa80bbb3ff0544a5a29172b3dae895ae schema:volumeNumber 2018
56 rdf:type schema:PublicationVolume
57 Ndb567358fd574e6780e5b73e53ddd6c9 schema:name dimensions_id
58 schema:value pub.1110668203
59 rdf:type schema:PropertyValue
60 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
61 schema:name Psychology and Cognitive Sciences
62 rdf:type schema:DefinedTerm
63 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
64 schema:name Psychology
65 rdf:type schema:DefinedTerm
66 sg:journal.1052482 schema:issn 1029-8479
67 1126-6708
68 schema:name Journal of High Energy Physics
69 rdf:type schema:Periodical
70 sg:person.010300415037.23 schema:affiliation https://www.grid.ac/institutes/grid.5254.6
71 schema:familyName Monk
72 schema:givenName J. W.
73 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010300415037.23
74 rdf:type schema:Person
75 sg:pub.10.1007/jhep01(2017)110 schema:sameAs https://app.dimensions.ai/details/publication/pub.1074216551
76 https://doi.org/10.1007/jhep01(2017)110
77 rdf:type schema:CreativeWork
78 sg:pub.10.1007/jhep07(2016)069 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045717527
79 https://doi.org/10.1007/jhep07(2016)069
80 rdf:type schema:CreativeWork
81 sg:pub.10.1007/s41781-017-0004-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091994251
82 https://doi.org/10.1007/s41781-017-0004-6
83 rdf:type schema:CreativeWork
84 sg:pub.10.1088/1126-6708/2008/03/038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031316682
85 https://doi.org/10.1088/1126-6708/2008/03/038
86 rdf:type schema:CreativeWork
87 sg:pub.10.1088/1126-6708/2008/12/039 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050931083
88 https://doi.org/10.1088/1126-6708/2008/12/039
89 rdf:type schema:CreativeWork
90 sg:pub.10.1088/1126-6708/2009/05/053 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002941310
91 https://doi.org/10.1088/1126-6708/2009/05/053
92 rdf:type schema:CreativeWork
93 sg:pub.10.1088/1126-6708/2009/11/038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019772541
94 https://doi.org/10.1088/1126-6708/2009/11/038
95 rdf:type schema:CreativeWork
96 sg:pub.10.1140/epjc/s10052-008-0798-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047392024
97 https://doi.org/10.1140/epjc/s10052-008-0798-9
98 rdf:type schema:CreativeWork
99 sg:pub.10.1140/epjc/s10052-012-1896-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009624676
100 https://doi.org/10.1140/epjc/s10052-012-1896-2
101 rdf:type schema:CreativeWork
102 https://doi.org/10.1016/0167-2789(84)90245-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039676522
103 rdf:type schema:CreativeWork
104 https://doi.org/10.1016/0167-2789(90)90175-o schema:sameAs https://app.dimensions.ai/details/publication/pub.1034195333
105 rdf:type schema:CreativeWork
106 https://doi.org/10.1016/0550-3213(84)90463-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006667108
107 rdf:type schema:CreativeWork
108 https://doi.org/10.1016/0550-3213(88)90089-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039919508
109 rdf:type schema:CreativeWork
110 https://doi.org/10.1016/j.cpc.2013.05.021 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011366723
111 rdf:type schema:CreativeWork
112 https://doi.org/10.1103/physrevd.48.3160 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006547860
113 rdf:type schema:CreativeWork
114 https://doi.org/10.1103/physrevd.87.054012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035956013
115 rdf:type schema:CreativeWork
116 https://www.grid.ac/institutes/grid.5254.6 schema:alternateName University of Copenhagen
117 schema:name Niels Bohr Institute, University of Copenhagen, Blegdamsvej, Copenhagen, Denmark
118 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...