TY  - EJOUR
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-2020-03975
PY  - 2020
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.
LB  - PUB:(DE-HGF)25
UR  - https://juser.fz-juelich.de/record/885634
ER  -