paper-with-me

홈 › Papers

Constraining Chaos: Enforcing dynamical invariants in the training of recurrent neural networks

2023-04-24 · Jason A. Platt, Stephen G. Penny, Timothy A. Smith, Tse-Chun Chen, Henry D. I. Abarbanel

Drawing on ergodic theory, we introduce a novel training method for machine learning based forecasting methods for chaotic dynamical systems. The training enforces dynamical invariants--such as the Lyapunov exponent spectrum and fractal dimension--in the systems of interest, enabling longer and more stable forecasts when operating with limited data. The technique is demonstrated in detail using the recurrent neural network architecture of reservoir computing. Results are given for the Lorenz 1996 chaotic dynamical system and a spectral quasi-geostrophic model, both typical test cases for numerical weather prediction.

📄 PDF Abstract BibTeX arXiv:2304.12865

Code (1)

japlatt/basicreservoircomputing 공식 구현

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

A Logic-Driven Framework for Consistency of Neural Models

2019-08-31 · IJCNLP 2019 11 · Tao Li, Vivek Gupta, Maitrey Mehta, Vivek Srikumar

While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples. In this paper, we formalize such inconsistency as a generalization of prediction error. …

Natural Language Inference

A Frobenius-Optimal Projection for Enforcing Linear Conservation in Learned Dynamical Models

2025-12-26 · John M. Mango, Ronald Katende arxiv

We consider the problem of restoring linear conservation laws in data-driven linear dynamical models. Given a learned operator $\widehat{A}$ and a full-rank constraint matrix $C$ encoding one or more invariants, we show …

Koopman Invariants as Drivers of Emergent Time-Series Clustering in Joint-Embedding Predictive Architectures

2025-11-12 · Pablo Ruiz-Morales, Dries Vanoost, Davy Pissoort, Mathias Verbeke arxiv

Joint-Embedding Predictive Architectures (JEPAs), a powerful class of self-supervised models, exhibit an unexplained ability to cluster time-series data by their underlying dynamical regimes. We propose a novel theoretic…

Self-Supervised Learning

Model scale versus domain knowledge in statistical forecasting of chaotic systems

2023-03-13 · William Gilpin

Chaos and unpredictability are traditionally synonymous, yet large-scale machine learning methods recently have demonstrated a surprising ability to forecast chaotic systems well beyond typical predictability horizons. H…

Time SeriesTime Series AnalysisTime Series Forecasting

Mutual Information and the Edge of Chaos in Reservoir Computers

2019-06-06 · Thomas L. Carroll

A reservoir computer is a dynamical system that may be used to perform computations. A reservoir computer usually consists of a set of nonlinear nodes coupled together in a network so that there are feedback paths. Train…

Time SeriesTime Series Analysis