Organization of computation in reservoir computing

• URL: http://arxiv.org/abs/2607.17858v1
• Date: Mon, 20 Jul 2026 11:59:11 GMT
• Title: Organization of computation in reservoir computing
• Abstract summary: Reservoir computing exploits nonlinear dynamical systems to encode temporal inputs into state space representations.<n>We introduce an eigen-spectral decomposition framework linking the degree-wise information processing capacity to the corresponding state space modes.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reservoir computing exploits nonlinear dynamical systems to encode temporal inputs into high-dimensional state space representations. Although reservoir performance is often characterized through memory, nonlinearity, and their tradeoff, such aggregate measures do not reveal how task-relevant information is organized within the state space. Here, we introduce an eigen-spectral decomposition framework linking the degree-wise information processing capacity to the corresponding state space modes. As a result, we are able to quantify the degree-wise representation energy, and show that in some cases, substantial amounts of information processing capacity may reside in low-energy modes that are vulnerable to experimental noise. These results suggest that useful reservoir computation depends not only on dimensionality expansion, but also on the geometric organization of task-relevant information, with direct implications on physical reservoir computers.

Related papers

• Energetic Cost of Temporal Information Processing in Quantum Reservoirs [0.47248250311484113]
  Quantum reservoir computing offers a promising route toward energy-efficient machine learning.<n>We show that, in an interacting spin reservoir, information encoding and information processing are governed by distinct physical mechanisms.
  arXiv  Detail & Related papers  (2026-08-08T18:21:33Z)
• Geometric Approach to Zero-Memory Quantum Dot Reservoir Computing [0.11999555634662634]
  Physical reservoir computing offers an energy-efficient alternative to conventional neural networks.<n>We show that memory capacity can be engineered extrinsically in memoryless systems.<n>We show that memoryless quantum reservoir can achieve high performance on both chaotic Mackey-Glass future prediction and nonlinear transformation tasks.
  arXiv  Detail & Related papers  (2026-06-28T10:26:43Z)
• Illuminating the Black Box of Reservoir Computing [2.925652638976278]
  This study aims to identify the minimal computational ingredients required for different model tasks.<n>We examine how many neurons, how much nonlinearity, and which connective structure is necessary.<n>Surprisingly, we find non-trivial cases where the readout layer performs the bulk of the computation.
  arXiv  Detail & Related papers  (2025-11-21T07:13:26Z)
• Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systems [49.819436680336786]
  We propose an efficient transformed Gaussian process state-space model (ETGPSSM) for scalable and flexible modeling of high-dimensional, non-stationary dynamical systems.<n>Specifically, our ETGPSSM integrates a single shared GP with input-dependent normalizing flows, yielding an expressive implicit process prior that captures complex, non-stationary transition dynamics.<n>Our ETGPSSM outperforms existing GPSSMs and neural network-based SSMs in terms of computational efficiency and accuracy.
  arXiv  Detail & Related papers  (2025-03-24T03:19:45Z)
• Deep Photonic Reservoir Computer for Speech Recognition [49.1574468325115]
  Speech recognition is a critical task in the field of artificial intelligence and has witnessed remarkable advancements. Deep reservoir computing is energy efficient but exhibits limitations in performance when compared to more resource-intensive machine learning algorithms. We propose a photonic-based deep reservoir computer and evaluate its effectiveness on different speech recognition tasks.
  arXiv  Detail & Related papers  (2023-12-11T17:43:58Z)
• Discrete, compositional, and symbolic representations through attractor dynamics [51.20712945239422]
  We introduce a novel neural systems model that integrates attractor dynamics with symbolic representations to model cognitive processes akin to the probabilistic language of thought (PLoT) Our model segments the continuous representational space into discrete basins, with attractor states corresponding to symbolic sequences, that reflect the semanticity and compositionality characteristic of symbolic systems through unsupervised learning, rather than relying on pre-defined primitives. This approach establishes a unified framework that integrates both symbolic and sub-symbolic processing through neural dynamics, a neuroplausible substrate with proven expressivity in AI, offering a more comprehensive model that mirrors the complex duality of cognitive operations
  arXiv  Detail & Related papers  (2023-10-03T05:40:56Z)
• Restrictions on Physical Stochastic Reservoir Computers [0.0]
  We study the impact of noise on the learning capabilities of analog reservoir computers.<n>We show that the information processing capacity (IPC) is a useful metric for quantifying the degradation of the performance due to noise.<n>We conclude that any physical, analog reservoir computer that is exposed to noise can only be used to perform a amount of learning.
  arXiv  Detail & Related papers  (2023-07-26T19:41:05Z)
• Machine learning at the mesoscale: a computation-dissipation bottleneck [77.34726150561087]
  We study a computation-dissipation bottleneck in mesoscopic systems used as input-output devices. Our framework sheds light on a crucial compromise between information compression, input-output computation and dynamic irreversibility induced by non-reciprocal interactions.
  arXiv  Detail & Related papers  (2023-07-05T15:46:07Z)
• Natural quantum reservoir computing for temporal information processing [4.785845498722406]
  Reservoir computing is a temporal information processing system that exploits artificial or physical dissipative dynamics. This paper proposes the use of real superconducting quantum computing devices as the reservoir, where the dissipative property is served by the natural noise added to the quantum bits.
  arXiv  Detail & Related papers  (2021-07-13T01:58:57Z)
• Featurized Density Ratio Estimation [82.40706152910292]
  In our work, we propose to leverage an invertible generative model to map the two distributions into a common feature space prior to estimation. This featurization brings the densities closer together in latent space, sidestepping pathological scenarios where the learned density ratios in input space can be arbitrarily inaccurate. At the same time, the invertibility of our feature map guarantees that the ratios computed in feature space are equivalent to those in input space.
  arXiv  Detail & Related papers  (2021-07-05T18:30:26Z)
• Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders [63.46738617561255]
  We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder. We use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not. Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique.
  arXiv  Detail & Related papers  (2020-10-19T01:27:21Z)
• Information-Theoretic Memory Scaling in the Many-Body Localization Transition [68.8204255655161]
  We study the understanding of local memory in the context of many-body localization. We introduce the dynamical Holevo quantity as the true quantifier of local memory. We find clear scaling behavior in its steady-state across the many-body localization transition.
  arXiv  Detail & Related papers  (2020-09-09T18:00:01Z)
• Focus of Attention Improves Information Transfer in Visual Features [80.22965663534556]
  This paper focuses on unsupervised learning for transferring visual information in a truly online setting. The computation of the entropy terms is carried out by a temporal process which yields online estimation of the entropy terms. In order to better structure the input probability distribution, we use a human-like focus of attention model.
  arXiv  Detail & Related papers  (2020-06-16T15:07:25Z)

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.