Exploring the origins of switching dynamics in a multifunctional reservoir computer

Andrew Flynn, Andreas Amann
8/27/2024
math.DScs.LGcs.NE

No confident code implementation found for this paper.

Abstract

The concept of multifunctionality has enabled reservoir computers (RCs), a type of dynamical system that is typically realised as an artificial neural network, to reconstruct multiple attractors simultaneously using the same set of trained weights. However there are many additional phenomena that arise when training a RC to reconstruct more than one attractor. Previous studies have found that, in certain cases, if the RC fails to reconstruct a coexistence of attractors then it exhibits a form of metastability whereby, without any external input, the state of the RC switches between different modes of behaviour that resemble properties of the attractors it failed to reconstruct. In this paper we explore the origins of these switching dynamics in a paradigmatic setting via the `seeing double' problem.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Seeing double with a multifunctional reservoir computer

91% match2023

Multifunctionality in a Connectome-Based Reservoir Computer

85% match2023

Confabulation dynamics in a reservoir computer: Filling in the gaps with untrained attractors

84% match2025

Attractor-merging Crises and Intermittency in Reservoir Computing

82% match2025

Multifunctional physical reservoir computing in soft tensegrity robots

78% match2025

Reservoir Computing Generalized

78% match2024

Cite this paper

@article{flynn2024exploring,
  title  = {Exploring the origins of switching dynamics in a multifunctional reservoir computer},
  author = {Andrew Flynn and Andreas Amann},
  year   = {2024},
  eprint = {2408.15400},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.15400v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.15400.svg)](https://codeofpaper.com/paper/2408.15400)

Discussion