% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Nestler:885634,
author = {Nestler, Sandra and Keup, Christian and Dahmen, David and
Gilson, Matthieu and Rauhut, Holger and Helias, Moritz},
title = {{U}nfolding recurrence by {G}reen's functions for optimized
reservoir computing},
reportid = {FZJ-2020-03975},
year = {2020},
abstract = {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.},
cin = {INM-6 / IAS-6 / INM-10},
cid = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828 /
I:(DE-Juel1)INM-10-20170113},
pnm = {574 - Theory, modelling and simulation (POF3-574) / HBP
SGA3 - Human Brain Project Specific Grant Agreement 3
(945539) / neuroIC002 - Recurrence and stochasticity for
neuro-inspired computation (EXS-SF-neuroIC002) / Advanced
Computing Architectures $(aca_20190115)$ / RenormalizedFlows
- Transparent Deep Learning with Renormalized Flows
(BMBF-01IS19077A) / SDS005 - Towards an integrated data
science of complex natural systems (PF-JARA-SDS005) / PhD no
Grant - Doktorand ohne besondere Förderung
(PHD-NO-GRANT-20170405)},
pid = {G:(DE-HGF)POF3-574 / G:(EU-Grant)945539 /
G:(DE-82)EXS-SF-neuroIC002 / $G:(DE-Juel1)aca_20190115$ /
G:(DE-Juel-1)BMBF-01IS19077A / G:(DE-Juel-1)PF-JARA-SDS005 /
G:(DE-Juel1)PHD-NO-GRANT-20170405},
typ = {PUB:(DE-HGF)25},
eprint = {2010.06247},
howpublished = {arXiv:2010.06247},
archivePrefix = {arXiv},
SLACcitation = {$\%\%CITATION$ = $arXiv:2010.06247;\%\%$},
url = {https://juser.fz-juelich.de/record/885634},
}