Hauptseite > Publikationsdatenbank > Neural networks learning structure in temporal signals > print

001     1006605
005     20240313095011.0
037 _ _ |a FZJ-2023-01742
041 _ _ |a English
100 1 _ |a Nestler, Sandra
|0 P:(DE-Juel1)174585
|b 0
|e Corresponding author
|u fzj
111 2 _ |a Seminar Talk, Barak Lab
|c Haifa
|w Israel
245 _ _ |a Neural networks learning structure in temporal signals
|f 2023-02-28 -
260 _ _ |c 2023
336 7 _ |a Conference Paper
|0 33
|2 EndNote
336 7 _ |a Other
|2 DataCite
336 7 _ |a INPROCEEDINGS
|2 BibTeX
336 7 _ |a LECTURE_SPEECH
|2 ORCID
336 7 _ |a Talk (non-conference)
|b talk
|m talk
|0 PUB:(DE-HGF)31
|s 1683183034_28115
|2 PUB:(DE-HGF)
|x Invited
336 7 _ |a Other
|2 DINI
520 _ _ |a Cortical networks are strongly recurrent, and neurons have intrinsic temporal dynamics. This sets them apart from deep feed-forward networks. Despite the tremendous progress in the application of feed-forward networks and their theoretical understanding, it remains unclear how the interplay of recurrence and non-linearities in recurrent cortical networks contributes to their function. The purpose of this work is to present a solvable recurrent network model that links to feed forward networks. By perturbative methods we transform the time-continuous,recurrent dynamics into an effective feed-forward structure of linear and non-linear temporal kernels. The resulting analytical expressions allow us to build optimal time-series classifiers from random reservoir networks. Firstly, this allows us to optimize not only the readout vectors, but also the input projection, demonstrating a strong potential performance gain. Secondly, the analysis exposes how the second order stimulus statistics is a crucial element that interacts with the non-linearity of the dynamics and boosts performance.
536 _ _ |a 5231 - Neuroscientific Foundations (POF4-523)
|0 G:(DE-HGF)POF4-5231
|c POF4-523
|f POF IV
|x 0
536 _ _ |a 5232 - Computational Principles (POF4-523)
|0 G:(DE-HGF)POF4-5232
|c POF4-523
|f POF IV
|x 1
536 _ _ |a 5234 - Emerging NC Architectures (POF4-523)
|0 G:(DE-HGF)POF4-5234
|c POF4-523
|f POF IV
|x 2
536 _ _ |a HBP SGA3 - Human Brain Project Specific Grant Agreement 3 (945539)
|0 G:(EU-Grant)945539
|c 945539
|f H2020-SGA-FETFLAG-HBP-2019
|x 3
536 _ _ |a ACA - Advanced Computing Architectures (SO-092)
|0 G:(DE-HGF)SO-092
|c SO-092
|x 4
536 _ _ |a RenormalizedFlows - Transparent Deep Learning with Renormalized Flows (BMBF-01IS19077A)
|0 G:(DE-Juel-1)BMBF-01IS19077A
|c BMBF-01IS19077A
|x 5
536 _ _ |a SDS005 - Towards an integrated data science of complex natural systems (PF-JARA-SDS005)
|0 G:(DE-Juel-1)PF-JARA-SDS005
|c PF-JARA-SDS005
|x 6
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 7
700 1 _ |a Keup, Christian
|0 P:(DE-Juel1)171384
|b 1
|u fzj
700 1 _ |a Dahmen, David
|0 P:(DE-Juel1)156459
|b 2
|u fzj
700 1 _ |a Gilson, Matthieu
|0 P:(DE-Juel1)184621
|b 3
700 1 _ |a Rauhut, Holger
|0 P:(DE-HGF)0
|b 4
700 1 _ |a Helias, Moritz
|0 P:(DE-Juel1)144806
|b 5
|u fzj
700 1 _ |a Bartolomaeus, Wiebke
|0 P:(DE-HGF)0
|b 6
700 1 _ |a Boutaib, Youness
|0 P:(DE-HGF)0
|b 7
700 1 _ |a Bouss, Peter
|0 P:(DE-Juel1)178725
|b 8
|u fzj
700 1 _ |a Merger, Claudia Lioba
|0 P:(DE-Juel1)184900
|b 9
|u fzj
700 1 _ |a Fischer, Kirsten
|0 P:(DE-Juel1)180150
|b 10
|u fzj
700 1 _ |a Rene, Alexandre
|0 P:(DE-Juel1)178936
|b 11
|u fzj
700 1 _ |a Schirrmeister, Robin
|0 P:(DE-HGF)0
|b 12
700 1 _ |a Ball, Tonio
|0 P:(DE-HGF)0
|b 13
909 C O |o oai:juser.fz-juelich.de:1006605
|p openaire
|p VDB
|p ec_fundedresources
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 0
|6 P:(DE-Juel1)174585
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 1
|6 P:(DE-Juel1)171384
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 2
|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
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 8
|6 P:(DE-Juel1)178725
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 9
|6 P:(DE-Juel1)184900
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 10
|6 P:(DE-Juel1)180150
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 11
|6 P:(DE-Juel1)178936
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)POF4-5231
|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)POF4-5232
|x 1
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 2
914 1 _ |y 2023
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 _ _ |a talk
980 _ _ |a VDB
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 UNRESTRICTED
981 _ _ |a I:(DE-Juel1)IAS-6-20130828

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21