Storage and selection of multiple chaotic attractors in minimal reservoir computers

• URL: http://arxiv.org/abs/2603.15155v1
• Date: Mon, 16 Mar 2026 11:49:14 GMT
• Title: Storage and selection of multiple chaotic attractors in minimal reservoir computers
• Abstract summary: Multi-attractor learning has largely been pursued using large, randomly wired reservoirs.<n>Recent work shows that minimal deterministic reservoirs can match random designs for single-system chaotic forecasting.<n>We find that minimal architectures can successfully store multiple chaotic attractors, but struggle with task switching.
• Score: 0.4390824340015486
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern predictive modeling increasingly calls for a single learned dynamical substrate to operate across multiple regimes. From a dynamical-systems viewpoint, this capability decomposes into the storage of multiple attractors and the selection of the appropriate attractor in response to contextual cues. In reservoir computing (RC), multi-attractor learning has largely been pursued using large, randomly wired reservoirs, on the assumption that stochastic connectivity is required to generate sufficiently rich internal dynamics. At the same time, recent work shows that minimal deterministic reservoirs can match random designs for single-system chaotic forecasting. Under which conditions can minimal topologies learn multiple chaotic attractors? In this paper, we find that minimal architectures can successfully store multiple chaotic attractors. However, these same architectures struggle with task switching, in which the system must transition between attractors in response to external cues. We test storage and selection on all 28 unordered system pairs formed from eight three-dimensional chaotic systems. We do not observe a robust dependence of multi-attractor performance on reservoir topology. Over the ten topologies investigated, we find that no single one consistently outperforms the others for either storage or cue-dependent selection. Our results suggest that while minimal substrates possess the representational capacity to model coexisting attractors, they may lack the robust temporal memory required for cued transitions.

Related papers

• Reservoir Computing via Multi-Scale Random Fourier Features for Forecasting Fast-Slow Dynamical Systems [0.0]
  We present a novel reservoir computing framework that combines delay embedding with random Fourier feature (RFF) mappings to capture such dynamics.<n>Two formulations are investigated: a single-scale RFF reservoir, which employs a fixed kernel bandwidth, and a multi-scale RFF reservoir, which integrates multiple bandwidths to represent both fast and slow temporal dependencies.
  arXiv  Detail & Related papers  (2025-11-04T08:01:08Z)
• Multi-Modal Manipulation via Multi-Modal Policy Consensus [62.49978559936122]
  We propose a new approach to integrate diverse sensory modalities for robotic manipulation.<n>Our method factorizes the policy into a set of diffusion models, each specialized for a single representation.<n>We evaluate our approach on simulated manipulation tasks in RLBench, as well as real-world tasks such as occluded object picking, in-hand spoon reorientation, and puzzle insertion.
  arXiv  Detail & Related papers  (2025-09-27T19:43:04Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• Robustly optimal dynamics for active matter reservoir computing [0.0]
  Information processing abilities of active matter are studied in the reservoir computing paradigm to infer the future state of a chaotic signal.<n>We uncover an exceptional regime of agent dynamics that has been overlooked previously.<n>It appears robustly optimal for performance under many conditions, thus providing valuable insights into computation with physical systems more generally.
  arXiv  Detail & Related papers  (2025-05-08T17:09:14Z)
• Exploring the origins of switching dynamics in a multifunctional reservoir computer [0.0]
  Reservoir computers (RCs) reconstruct multiple attractors simultaneously using the same set of trained weights. In certain cases, if the RC fails to reconstruct a coexistence of attractors then it exhibits a form of metastability. This paper explores the origins of these switching dynamics in a paradigmatic setting via the seeing double' problem.
  arXiv  Detail & Related papers  (2024-08-27T20:51:48Z)
• Hybrid Recurrent Models Support Emergent Descriptions for Hierarchical Planning and Control [0.8749675983608172]
  A class of hybrid state-space model known as recurrent switching linear dynamical systems (rSLDS) discovers meaningful behavioural units. We propose that the rich representations formed by an rSLDS can provide useful abstractions for planning and control. We present a novel hierarchical model-based algorithm inspired by Active Inference in which a discrete MDP sits above a low-level linear-quadratic controller.
  arXiv  Detail & Related papers  (2024-08-20T16:02:54Z)
• Chaotic attractor reconstruction using small reservoirs - the influence of topology [0.0]
  Reservoir computing has been shown to be an effective method of forecasting chaotic dynamics. We show that a reservoir of uncoupled nodes more reliably produces long term timeseries predictions.
  arXiv  Detail & Related papers  (2024-02-23T09:43:52Z)
• Endogenous Macrodynamics in Algorithmic Recourse [52.87956177581998]
  Existing work on Counterfactual Explanations (CE) and Algorithmic Recourse (AR) has largely focused on single individuals in a static environment. We show that many of the existing methodologies can be collectively described by a generalized framework. We then argue that the existing framework does not account for a hidden external cost of recourse, that only reveals itself when studying the endogenous dynamics of recourse at the group level.
  arXiv  Detail & Related papers  (2023-08-16T07:36:58Z)
• Seeing double with a multifunctional reservoir computer [0.0]
  Multifunctional biological neural networks exploit multistability in order to perform multiple tasks without changing any network properties. We study how a reservoir computer reconstructs a coexistence of attractors when there is an overlap between them. A bifurcation analysis reveals how multifunctionality emerges and is destroyed as the RC enters a chaotic regime.
  arXiv  Detail & Related papers  (2023-05-09T23:10:29Z)
• Automated Search for Resource-Efficient Branched Multi-Task Networks [81.48051635183916]
  We propose a principled approach, rooted in differentiable neural architecture search, to automatically define branching structures in a multi-task neural network. We show that our approach consistently finds high-performing branching structures within limited resource budgets.
  arXiv  Detail & Related papers  (2020-08-24T09:49:19Z)
• S2RMs: Spatially Structured Recurrent Modules [105.0377129434636]
  We take a step towards exploiting dynamic structure that are capable of simultaneously exploiting both modular andtemporal structures. We find our models to be robust to the number of available views and better capable of generalization to novel tasks without additional training.
  arXiv  Detail & Related papers  (2020-07-13T17:44:30Z)
• Unsupervised multi-modal Styled Content Generation [61.040392094140245]
  UMMGAN is a novel architecture designed to better model multi-modal distributions in an unsupervised fashion. We show that UMMGAN effectively disentangles between modes and style, thereby providing an independent degree of control over the generated content.
  arXiv  Detail & Related papers  (2020-01-10T19:36:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.