Home > Publications database > Decomposing neural networks as mappings of correlation functions > print

001     912163
005     20240313103120.0
024 7 _ |a 10.1103/PhysRevResearch.4.043143
|2 doi
024 7 _ |a 2128/32946
|2 Handle
024 7 _ |a WOS:000933947400011
|2 WOS
037 _ _ |a FZJ-2022-05381
082 _ _ |a 530
100 1 _ |a Fischer, Kirsten
|0 P:(DE-Juel1)180150
|b 0
|e Corresponding author
245 _ _ |a Decomposing neural networks as mappings of correlation functions
260 _ _ |a College Park, MD
|c 2022
|b APS
336 7 _ |a article
|2 DRIVER
336 7 _ |a Output Types/Journal article
|2 DataCite
336 7 _ |a Journal Article
|b journal
|m journal
|0 PUB:(DE-HGF)16
|s 1670307479_6446
|2 PUB:(DE-HGF)
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a JOURNAL_ARTICLE
|2 ORCID
336 7 _ |a Journal Article
|0 0
|2 EndNote
520 _ _ |a Understanding the functional principles of information processing in deep neural networks continues to be a challenge, in particular for networks with trained and thus nonrandom weights. To address this issue, we study the mapping between probability distributions implemented by a deep feed-forward network. We characterize this mapping as an iterated transformation of distributions, where the nonlinearity in each layer transfers information between different orders of correlation functions. This allows us to identify essential statistics in the data, as well as different information representations that can be used by neural networks. Applied to an XOR task and to MNIST, we show that correlations up to second order predominantly capture the information processing in the internal layers, while the input layer also extracts higher-order correlations from the data. This analysis provides a quantitative and explainable perspective on classification.
536 _ _ |a 5232 - Computational Principles (POF4-523)
|0 G:(DE-HGF)POF4-5232
|c POF4-523
|f POF IV
|x 0
536 _ _ |a 5234 - Emerging NC Architectures (POF4-523)
|0 G:(DE-HGF)POF4-5234
|c POF4-523
|f POF IV
|x 1
536 _ _ |a RenormalizedFlows - Transparent Deep Learning with Renormalized Flows (BMBF-01IS19077A)
|0 G:(DE-Juel-1)BMBF-01IS19077A
|c BMBF-01IS19077A
|x 2
536 _ _ |a MSNN - Theory of multi-scale neuronal networks (HGF-SMHB-2014-2018)
|0 G:(DE-Juel1)HGF-SMHB-2014-2018
|c HGF-SMHB-2014-2018
|f MSNN
|x 3
536 _ _ |a ACA - Advanced Computing Architectures (SO-092)
|0 G:(DE-HGF)SO-092
|c SO-092
|x 4
536 _ _ |a neuroIC002 - Recurrence and stochasticity for neuro-inspired computation (EXS-SF-neuroIC002)
|0 G:(DE-82)EXS-SF-neuroIC002
|c EXS-SF-neuroIC002
|x 5
588 _ _ |a Dataset connected to CrossRef, Journals: juser.fz-juelich.de
700 1 _ |a René, Alexandre
|0 P:(DE-Juel1)178936
|b 1
|u fzj
700 1 _ |a Keup, Christian
|0 P:(DE-Juel1)171384
|b 2
700 1 _ |a Layer, Moritz
|0 P:(DE-Juel1)174497
|b 3
700 1 _ |a Dahmen, David
|0 P:(DE-Juel1)156459
|b 4
700 1 _ |a Helias, Moritz
|0 P:(DE-Juel1)144806
|b 5
773 _ _ |a 10.1103/PhysRevResearch.4.043143
|g Vol. 4, no. 4, p. 043143
|0 PERI:(DE-600)3004165-X
|n 4
|p 043143
|t Physical review research
|v 4
|y 2022
|x 2643-1564
856 4 _ |y OpenAccess
|u https://juser.fz-juelich.de/record/912163/files/Fischer_2022_prr.pdf
856 4 _ |y OpenAccess
|u https://juser.fz-juelich.de/record/912163/files/PhysRevResearch.4.043143.pdf
909 C O |o oai:juser.fz-juelich.de:912163
|p openaire
|p open_access
|p OpenAPC
|p driver
|p VDB
|p openCost
|p dnbdelivery
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 0
|6 P:(DE-Juel1)180150
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 1
|6 P:(DE-Juel1)178936
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 2
|6 P:(DE-Juel1)171384
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 3
|6 P:(DE-Juel1)174497
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 4
|6 P:(DE-Juel1)156459
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 5
|6 P:(DE-Juel1)144806
913 1 _ |a DE-HGF
|b Key Technologies
|l Natural, Artificial and Cognitive Information Processing
|1 G:(DE-HGF)POF4-520
|0 G:(DE-HGF)POF4-523
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-500
|4 G:(DE-HGF)POF
|v Neuromorphic Computing and Network Dynamics
|9 G:(DE-HGF)POF4-5232
|x 0
913 1 _ |a DE-HGF
|b Key Technologies
|l Natural, Artificial and Cognitive Information Processing
|1 G:(DE-HGF)POF4-520
|0 G:(DE-HGF)POF4-523
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-500
|4 G:(DE-HGF)POF
|v Neuromorphic Computing and Network Dynamics
|9 G:(DE-HGF)POF4-5234
|x 1
914 1 _ |y 2022
915 p c |a Local Funding
|2 APC
|0 PC:(DE-HGF)0001
915 p c |a DFG OA Publikationskosten
|2 APC
|0 PC:(DE-HGF)0002
915 _ _ |a OpenAccess
|0 StatID:(DE-HGF)0510
|2 StatID
915 _ _ |a Creative Commons Attribution CC BY 4.0
|0 LIC:(DE-HGF)CCBY4
|2 HGFVOC
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0200
|2 StatID
|b SCOPUS
|d 2022-11-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0300
|2 StatID
|b Medline
|d 2022-11-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0501
|2 StatID
|b DOAJ Seal
|d 2022-08-16T10:08:58Z
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0500
|2 StatID
|b DOAJ
|d 2022-08-16T10:08:58Z
915 _ _ |a Peer Review
|0 StatID:(DE-HGF)0030
|2 StatID
|b DOAJ : Blind peer review
|d 2022-08-16T10:08:58Z
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0199
|2 StatID
|b Clarivate Analytics Master Journal List
|d 2022-11-29
915 _ _ |a WoS
|0 StatID:(DE-HGF)0112
|2 StatID
|b Emerging Sources Citation Index
|d 2022-11-29
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0150
|2 StatID
|b Web of Science Core Collection
|d 2022-11-29
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)INM-6-20090406
|k INM-6
|l Computational and Systems Neuroscience
|x 0
920 1 _ |0 I:(DE-Juel1)IAS-6-20130828
|k IAS-6
|l Theoretical Neuroscience
|x 1
920 1 _ |0 I:(DE-Juel1)INM-10-20170113
|k INM-10
|l Jara-Institut Brain structure-function relationships
|x 2
980 1 _ |a FullTexts
980 _ _ |a journal
980 _ _ |a VDB
980 _ _ |a UNRESTRICTED
980 _ _ |a I:(DE-Juel1)INM-6-20090406
980 _ _ |a I:(DE-Juel1)IAS-6-20130828
980 _ _ |a I:(DE-Juel1)INM-10-20170113
980 _ _ |a APC
981 _ _ |a I:(DE-Juel1)IAS-6-20130828

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21