000916669 001__ 916669
000916669 005__ 20240313095013.0
000916669 037__ $$aFZJ-2023-00020
000916669 041__ $$aEnglish
000916669 1001_ $$0P:(DE-Juel1)180150$$aFischer, Kirsten$$b0$$eCorresponding author$$ufzj
000916669 1112_ $$aQuantum Information Seminnar$$cAachen$$d2022-12-12 - 2022-12-12$$wGermany
000916669 245__ $$aDecomposing neural networks as mappings of correlation functions
000916669 260__ $$c2022
000916669 3367_ $$033$$2EndNote$$aConference Paper
000916669 3367_ $$2DataCite$$aOther
000916669 3367_ $$2BibTeX$$aINPROCEEDINGS
000916669 3367_ $$2ORCID$$aLECTURE_SPEECH
000916669 3367_ $$0PUB:(DE-HGF)31$$2PUB:(DE-HGF)$$aTalk (non-conference)$$btalk$$mtalk$$s1673261537_6371$$xInvited
000916669 3367_ $$2DINI$$aOther
000916669 520__ $$aUnderstanding the functional principles of information processing in deep neural networks continues to be a challenge, in particular for networks with trained and thus non-random 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 non-linearity 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.
000916669 536__ $$0G:(DE-HGF)POF4-5232$$a5232 - Computational Principles (POF4-523)$$cPOF4-523$$fPOF IV$$x0
000916669 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x1
000916669 536__ $$0G:(DE-Juel-1)BMBF-01IS19077A$$aRenormalizedFlows - Transparent Deep Learning with Renormalized Flows (BMBF-01IS19077A)$$cBMBF-01IS19077A$$x2
000916669 536__ $$0G:(DE-Juel1)HGF-SMHB-2014-2018$$aMSNN - Theory of multi-scale neuronal networks (HGF-SMHB-2014-2018)$$cHGF-SMHB-2014-2018$$fMSNN$$x3
000916669 536__ $$0G:(DE-HGF)SO-092$$aACA - Advanced Computing Architectures (SO-092)$$cSO-092$$x4
000916669 536__ $$0G:(DE-82)EXS-SF-neuroIC002$$aneuroIC002 - Recurrence and stochasticity for neuro-inspired computation (EXS-SF-neuroIC002)$$cEXS-SF-neuroIC002$$x5
000916669 7001_ $$0P:(DE-Juel1)178936$$aRene, Alexandre$$b1$$ufzj
000916669 7001_ $$0P:(DE-Juel1)171384$$aKeup, Christian$$b2$$ufzj
000916669 7001_ $$0P:(DE-Juel1)174497$$aLayer, Moritz$$b3$$ufzj
000916669 7001_ $$0P:(DE-Juel1)156459$$aDahmen, David$$b4$$ufzj
000916669 7001_ $$0P:(DE-Juel1)144806$$aHelias, Moritz$$b5$$ufzj
000916669 909CO $$ooai:juser.fz-juelich.de:916669$$pVDB
000916669 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180150$$aForschungszentrum Jülich$$b0$$kFZJ
000916669 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178936$$aForschungszentrum Jülich$$b1$$kFZJ
000916669 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171384$$aForschungszentrum Jülich$$b2$$kFZJ
000916669 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)174497$$aForschungszentrum Jülich$$b3$$kFZJ
000916669 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)156459$$aForschungszentrum Jülich$$b4$$kFZJ
000916669 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)144806$$aForschungszentrum Jülich$$b5$$kFZJ
000916669 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5232$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
000916669 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5234$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x1
000916669 9141_ $$y2022
000916669 920__ $$lyes
000916669 9201_ $$0I:(DE-Juel1)INM-6-20090406$$kINM-6$$lComputational and Systems Neuroscience$$x0
000916669 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lTheoretical Neuroscience$$x1
000916669 9201_ $$0I:(DE-Juel1)INM-10-20170113$$kINM-10$$lJara-Institut Brain structure-function relationships$$x2
000916669 980__ $$atalk
000916669 980__ $$aVDB
000916669 980__ $$aI:(DE-Juel1)INM-6-20090406
000916669 980__ $$aI:(DE-Juel1)IAS-6-20130828
000916669 980__ $$aI:(DE-Juel1)INM-10-20170113
000916669 980__ $$aUNRESTRICTED
000916669 981__ $$aI:(DE-Juel1)IAS-6-20130828