Weight statistics controls dynamics in recurrent neural networks.
Recurrent neural networks are complex non-linear systems, capable of ongoing activity in the absence of driving inputs. The dynamical properties of these systems, in particular their long-time attractor states, are determined on the microscopic level by the connection strengths wij between the indiv...
Main Authors: | Patrick Krauss, Marc Schuster, Verena Dietrich, Achim Schilling, Holger Schulze, Claus Metzner |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2019-01-01
|
Series: | PLoS ONE |
Online Access: | https://doi.org/10.1371/journal.pone.0214541 |
Similar Items
-
Dynamics and Information Import in Recurrent Neural Networks
by: Claus Metzner, et al.
Published: (2022-04-01) -
Recurrence Resonance” in Three-Neuron Motifs
by: Patrick Krauss, et al.
Published: (2019-09-01) -
Analysis of Structure and Dynamics in Three-Neuron Motifs
by: Patrick Krauss, et al.
Published: (2019-02-01) -
Sleep as a random walk: a super-statistical analysis of EEG data across sleep stages
by: Claus Metzner, et al.
Published: (2021-12-01) -
A New Statistical Approach for the Evaluation of Gap-prepulse Inhibition of the Acoustic Startle Reflex (GPIAS) for Tinnitus Assessment
by: Achim Schilling, et al.
Published: (2017-10-01)