Gast ::
| Hauptseite > Publikationsdatenbank > Unfolding recurrence by Green's functions for optimized reservoir computing |
| Hauptseite > Publikationsdatenbank > Unfolding recurrence by Green's functions for optimized reservoir computing |
| Preprint | FZJ-2020-03975 |
; ; ; ; ;
2020
This record in other databases:
Please use a persistent id in citations: http://hdl.handle.net/2128/25903
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.
|
The record appears in these collections: |
PDF
PDF (PDFA)