Random projection neural networks of best approximation: Convergence theory and practical applications
G Fabiani - arXiv preprint arXiv:2402.11397, 2024 - arxiv.org
We investigate the concept of Best Approximation for Feedforward Neural Networks (FNN)
and explore their convergence properties through the lens of Random Projection (RPNNs) …
and explore their convergence properties through the lens of Random Projection (RPNNs) …
Tipping points of evolving epidemiological networks: Machine learning-assisted, data-driven effective modeling
We study the tipping point collective dynamics of an adaptive susceptible–infected–
susceptible (SIS) epidemiological network in a data-driven, machine learning-assisted …
susceptible (SIS) epidemiological network in a data-driven, machine learning-assisted …
Machine Learning for the identification of phase-transitions in interacting agent-based systems
Deriving closed-form, analytical expressions for reduced-order models, and judiciously
choosing the closures leading to them, has long been the strategy of choice for studying …
choosing the closures leading to them, has long been the strategy of choice for studying …
A physics-informed neural network method for the approximation of slow invariant manifolds for the general class of stiff systems of ODEs
DG Patsatzis, L Russo, C Siettos - arXiv preprint arXiv:2403.11591, 2024 - arxiv.org
We present a physics-informed neural network (PINN) approach for the discovery of slow
invariant manifolds (SIMs), for the most general class of fast/slow dynamical systems of …
invariant manifolds (SIMs), for the most general class of fast/slow dynamical systems of …