Exploring the origins of switching dynamics in a multifunctional reservoir computer

• URL: http://arxiv.org/abs/2408.15400v1
• Date: Tue, 27 Aug 2024 20:51:48 GMT
• Title: Exploring the origins of switching dynamics in a multifunctional reservoir computer
• Authors: Andrew Flynn, Andreas Amann,
• Abstract summary: 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent [50.508669199496474]
  We develop a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We refine the agent through a ReST-like method that iteratively trains on previous trajectories. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model.
  arXiv  Detail & Related papers  (2023-12-15T18:20:15Z)
• Hybrid quantum-classical reservoir computing for simulating chaotic systems [2.4995929091995857]
  This work presents a hybrid quantum reservoir-computing framework, which replaces the quantum reservoir in RC with a quantum circuit circuit. The noiseless simulations of HQRC demonstrate valid prediction times comparable to state-of-the-art classical RC models.
  arXiv  Detail & Related papers  (2023-11-23T17:07:02Z)
• Inferring Relational Potentials in Interacting Systems [56.498417950856904]
  We propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions. NIIP assigns low energy to the subset of trajectories which respect the relational constraints observed. It allows trajectory manipulation, such as interchanging interaction types across separately trained models, as well as trajectory forecasting.
  arXiv  Detail & Related papers  (2023-10-23T00:44:17Z)
• Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control [63.310780486820796]
  We show how a parameterization of recurrent connectivity influences robustness in closed-loop settings. We find that closed-form continuous-time neural networks (CfCs) with fewer parameters can outperform their full-rank, fully-connected counterparts.
  arXiv  Detail & Related papers  (2023-10-05T21:44:18Z)
• 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)
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning [17.865755866792643]
  Reservoir computing (RC) is a recurrent neural network in which neurons are randomly connected. The model's rich dynamics, linear separability, and memory capacity then enable a simple linear readout to generate responses. RC spans areas far beyond machine learning, since it has been shown that the complex dynamics can be realized in various physical hardware implementations.
  arXiv  Detail & Related papers  (2023-07-27T05:20:20Z)
• 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)
• Exploring the limits of multifunctionality across different reservoir computers [0.0]
  We explore the performance of a continuous-time, leaky-integrator, and next-generation reservoir computer' (RC) We train each RC to reconstruct a coexistence of chaotic attractors from different dynamical systems. We examine the critical effects that certain parameters can have in each RC to achieve multifunctionality.
  arXiv  Detail & Related papers  (2022-05-23T15:06:38Z)
• A Predictive Coding Account for Chaotic Itinerancy [68.8204255655161]
  We show how a recurrent neural network implementing predictive coding can generate neural trajectories similar to chaotic itinerancy in the presence of input noise. We propose two scenarios generating random and past-independent attractor switching trajectories using our model.
  arXiv  Detail & Related papers  (2021-06-16T16:48:14Z)
• Reconstructing shared dynamics with a deep neural network [0.0]
  We present a method to identify hidden shared dynamics from time series by a two- module, feedforward neural network architecture. The method has the potential to reveal hidden components of dynamical systems, where experimental intervention is not possible.
  arXiv  Detail & Related papers  (2021-05-05T20:55:53Z)
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning [68.9515120904028]
  Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the building block.
  arXiv  Detail & Related papers  (2020-07-21T11:48:22Z)

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.