SINDy-Former: Data-driven identification of sparse dynamical models via cross-attention
Authors:
- Filippo FedericoniFFFilippo Federiconi
- Alessandro GiuseppiAGAlessandro Giuseppi
Open Access
- 1 August 2026
- journal article
- Published by KEAI Publishing in Journal of Automation and Intelligence
Abstract
No abstract availableFunding Information
- Sapienza Università di Roma
This publication has 12 references indexed in Scilit:
- Discovering governing equations from partial measurements with deep delay autoencodersProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2023
- Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and controlProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2022
- Transformers for modeling physical systemsNeural Networks, 2022
- Weak SINDy: Galerkin-Based Data-Driven Model SelectionMultiscale Modeling & Simulation, 2021
- SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamicsProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2020
- AI Feynman: A physics-inspired method for symbolic regressionScience Advances, 2020
- Discovering governing equations from data by sparse identification of nonlinear dynamical systemsProceedings of the National Academy of Sciences, 2016
- Eureqa: software reviewGenetic Programming and Evolvable Machines, 2010
- Dynamic mode decomposition of numerical and experimental dataJournal of Fluid Mechanics, 2010
- Distilling Free-Form Natural Laws from Experimental DataScience, 2009