Exploring the origins of switching dynamics in a multifunctional reservoir computer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Flynn, Andrew, Amann, Andreas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909299139149824
author Flynn, Andrew
Amann, Andreas
author_facet Flynn, Andrew
Amann, Andreas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15400
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring the origins of switching dynamics in a multifunctional reservoir computer
Flynn, Andrew
Amann, Andreas
Dynamical Systems
Machine Learning
Neural and Evolutionary Computing
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.
title Exploring the origins of switching dynamics in a multifunctional reservoir computer
topic Dynamical Systems
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2408.15400