paper-with-me

홈 › Papers

Geometric Principles for Machine Learning of Dynamical Systems

2025-02-19 · Zack Xuereb Conti, David J Wagg, Nick Pepper

Mathematical descriptions of dynamical systems are deeply rooted in topological spaces defined by non-Euclidean geometry. This paper proposes leveraging structure-rich geometric spaces for machine learning to achieve structural generalization when modeling physical systems from data, in contrast to embedding physics bias within model-free architectures. We consider model generalization to be a function of symmetry, invariance and uniqueness, defined as a topological mapping from state space dynamics to the parameter space. We illustrate this view through the machine learning of linear time-invariant dynamical systems, whose dynamics reside on the symmetric positive definite manifold.

📄 PDF Abstract BibTeX arXiv:2502.13895

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Modern Koopman Theory for Dynamical Systems

2021-02-24 · Steven L. Brunton, Marko Budišić, Eurika Kaiser, J. Nathan Kutz

The field of dynamical systems is being transformed by the mathematical tools and algorithms emerging from modern computing and data science. First-principles derivations and asymptotic reductions are giving way to data-…

BIG-bench Machine Learning

Feynman Machine: The Universal Dynamical Systems Computer

2016-09-13 · Eric Laukien, Richard Crowder, Fergal Byrne

Efforts at understanding the computational processes in the brain have met with limited success, despite their importance and potential uses in building intelligent machines. We propose a simple new model which draws on …

Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)

2025-02-28 · Yoonsoo Nam, Seok Hyeong Lee, Clementine C J Domine, Yeachan Park 외

In physics, complex systems are often simplified into minimal, solvable models that retain only the core principles. In machine learning, layerwise linear models (e.g., linear neural networks) act as simplified represent…

Position

GeoHNNs: Geometric Hamiltonian Neural Networks

2025-07-21 · Amine Mohamed Aboussalah, Abdessalam Ed-dib arxiv

The fundamental laws of physics are intrinsically geometric, dictating the evolution of systems through principles of symmetry and conservation. While modern machine learning offers powerful tools for modeling complex dy…

The Geometry of Cortical Computation: Manifold Disentanglement and Predictive Dynamics in VCNet

2025-08-05 · Brennen A. Hill, Zhang Xinyu, Timothy Putra Prasetio arxiv

Despite their success, modern convolutional neural networks (CNNs) exhibit fundamental limitations, including data inefficiency, poor out-of-distribution generalization, and vulnerability to adversarial perturbations. Th…

Image Classification