# Exploring the origins of switching dynamics in a multifunctional reservoir computer

arXiv: https://arxiv.org/abs/2408.15400 · HTML: https://mlsanity.com/paper/2408.15400/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 5 of 5)

- [Multifunctionality in a Reservoir Computer](https://mlsanity.com/paper/2008.06348/) (2020)
- [Seeing double with a multifunctional reservoir computer](https://mlsanity.com/paper/2305.05799/) (2023)
- [Exploring the limits of multifunctionality across different reservoir computers](https://mlsanity.com/paper/2205.11375/) (2022)
- [Multifunctionality in a Connectome-Based Reservoir Computer](https://mlsanity.com/paper/2306.01885/) (2023)
- [Dynamical properties and mechanisms of metastability: a perspective in neuroscience](https://mlsanity.com/paper/2305.05328/) (2023)

## Built on by (most cited first, 4 of 4)

- [Confabulation dynamics in a reservoir computer: Filling in the gaps with untrained attractors](https://mlsanity.com/paper/2505.04792/) (2025)
- [Attractor-merging Crises and Intermittency in Reservoir Computing](https://mlsanity.com/paper/2504.12695/) (2025)
- [Adaptive Sensing of Continuous Physical Systems for Machine Learning](https://mlsanity.com/paper/2603.03650/) (2026)
- [Storage and selection of multiple chaotic attractors in minimal reservoir computers](https://mlsanity.com/paper/2603.15155/) (2026)

## Abstract (arXiv)

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.