no code implementations • 19 Feb 2024 • Hector Vargas Alvarez, Gianluca Fabiani, Ioannis G. Kevrekidis, Nikolaos Kazantzis, Constantinos Siettos
We use Physics-Informed Neural Networks (PINNs) to solve the discrete-time nonlinear observer state estimation problem.
no code implementations • 17 Feb 2024 • Gianluca Fabiani
We investigate the concept of Best Approximation for Feedforward Neural Networks (FNN) and explore their convergence properties through the lens of Random Projection (RPNNs).
no code implementations • 25 Sep 2023 • Gianluca Fabiani, Nikolaos Evangelou, Tianqi Cui, Juan M. Bello-Rivas, Cristina P. Martin-Linares, Constantinos Siettos, Ioannis G. Kevrekidis
We present a machine learning (ML)-assisted framework bridging manifold learning, neural networks, Gaussian processes, and Equation-Free multiscale modeling, for (a) detecting tipping points in the emergent behavior of complex systems, and (b) characterizing probabilities of rare events (here, catastrophic shifts) near them.
no code implementations • 14 Sep 2023 • Dimitrios G. Patsatzis, Gianluca Fabiani, Lucia Russo, Constantinos Siettos
A comparison of the computational costs between symbolic, automatic and numerical approximation of the required derivatives in the learning process is also provided.
no code implementations • 21 Aug 2023 • Ferdinando Auricchio, Maria Roberta Belardo, Gianluca Fabiani, Francesco Calabrò, Ariel F. Pascaner
As expected, the accuracy of the approximation with a global polynomial increases only if the Chebychev nodes are considered.
no code implementations • 15 Mar 2023 • Hector Vargas Alvarez, Gianluca Fabiani, Nikolaos Kazantzis, Constantinos Siettos, Ioannis G. Kevrekidis
We assess the performance of the proposed PIML approach via a benchmark nonlinear discrete map for which the feedback linearization transformation law can be derived analytically; the example is characterized by steep gradients, due to the presence of singularities, in the domain of interest.
no code implementations • 10 Mar 2022 • Gianluca Fabiani, Evangelos Galaris, Lucia Russo, Constantinos Siettos
The unknown weights between the hidden and output layer are computed by Newton's iterations, using the Moore-Penrose pseudoinverse for low to medium, and sparse QR decomposition with regularization for medium to large scale systems.
no code implementations • 31 Jan 2022 • Evangelos Galaris, Gianluca Fabiani, Ioannis Gallos, Ioannis Kevrekidis, Constantinos Siettos
For our illustrations, we implemented the proposed method to construct the one-parameter bifurcation diagram of the 1D FitzHugh-Nagumo PDEs from data generated by $D1Q3$ Lattice Boltzmann simulations.
no code implementations • 3 Aug 2021 • Evangelos Galaris, Gianluca Fabiani, Francesco Calabrò, Daniela di Serafino, Constantinos Siettos
We propose a numerical method based on physics-informed Random Projection Neural Networks for the solution of Initial Value Problems (IVPs) of Ordinary Differential Equations (ODEs) with a focus on stiff problems.
no code implementations • 10 Dec 2020 • Francesco Calabrò, Gianluca Fabiani, Constantinos Siettos
We show that a feedforward neural network with a single hidden layer with sigmoidal functions and fixed, random, internal weights and biases can be used to compute accurately a collocation solution.
Numerical Analysis Numerical Analysis