Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Hamzi, Boumediene"'
Autor:
Grigoryeva, Lyudmila, Hamzi, Boumediene, Kemeth, Felix P., Kevrekidis, Yannis, Manjunath, G, Ortega, Juan-Pablo, Steynberg, Matthys J.
Using short histories of observations from a dynamical system, a workflow for the post-training initialization of reservoir computing systems is described. This strategy is called cold-starting, and it is based on a map called the starting map, which
Externí odkaz:
http://arxiv.org/abs/2403.10325
Arguments inspired by algorithmic information theory predict an inverse relation between the probability and complexity of output patterns in a wide range of input-output maps. This phenomenon is known as \emph{simplicity bias}. By viewing the parame
Externí odkaz:
http://arxiv.org/abs/2403.06989
Autor:
Hamzi, Boumediene, Dingle, Kamaludin
Simplicity bias is an intriguing phenomenon prevalent in various input-output maps, characterized by a preference for simpler, more regular, or symmetric outputs. Notably, these maps typically feature high-probability outputs with simple patterns, wh
Externí odkaz:
http://arxiv.org/abs/2401.00593
Publikováno v:
Physica D: Nonlinear Phenomena, 2024, 134153
Machine Learning (ML) and Algorithmic Information Theory (AIT) look at Complexity from different points of view. We explore the interface between AIT and Kernel Methods (that are prevalent in ML) by adopting an AIT perspective on the problem of learn
Externí odkaz:
http://arxiv.org/abs/2311.12624
In this paper, we deal with hypernormal forms of non-resonant double Hopf singularities. We investigate the infinite level normal form classification of such singularities with nonzero radial cubic part. We provide a normal form decomposition of norm
Externí odkaz:
http://arxiv.org/abs/2304.05739
Regressing the vector field of a dynamical system from a finite number of observed states is a natural way to learn surrogate models for such systems. A simple and interpretable way to learn a dynamical system from data is to interpolate its vector-f
Externí odkaz:
http://arxiv.org/abs/2301.10321
We consider the problem of learning Stochastic Differential Equations of the form $dX_t = f(X_t)dt+\sigma(X_t)dW_t $ from one sample trajectory. This problem is more challenging than learning deterministic dynamical systems because one sample traject
Externí odkaz:
http://arxiv.org/abs/2209.12086
To what extent can we forecast a time series without fitting to historical data? Can universal patterns of probability help in this task? Deep relations between pattern Kolmogorov complexity and pattern probability have recently been used to make \em
Externí odkaz:
http://arxiv.org/abs/2203.05391
Publikováno v:
In Physica D: Nonlinear Phenomena August 2024 464
Autor:
Hamzi, Boumediene, Dingle, Kamaludin
Publikováno v:
In Physica D: Nonlinear Phenomena July 2024 463