TY  - CONF
AU  - Nestler, Sandra
AU  - Keup, Christian
AU  - Dahmen, David
AU  - Gilson, Matthieu
AU  - Rauhut, Holger
AU  - Helias, Moritz
TI  - Unfolding recurrence by Green’s functions for optimized reservoir computing
M1  - FZJ-2021-02359
PY  - 2021
AB  - 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.
T2  - RNN seminar talk (online)
CY  - , Mortimer B. Zuckerman Mind Brain Behavior Institute (USA)
M2  - Mortimer B. Zuckerman Mind Brain Behavior Institute, USA
LB  - PUB:(DE-HGF)31
UR  - https://juser.fz-juelich.de/record/892802
ER  -