Recency-Weighted Temporally-Segmented Ensemble for Time-Series Modeling

1 code implementation • 4 Mar 2024 • Pål V. Johnsen, Eivind Bøhn, Sølve Eidnes, Filippo Remonato, Signe Riemer-Sørensen

Addressing this, we introduce the Recency-Weighted Temporally-Segmented (ReWTS, pronounced `roots') ensemble model, a novel chunk-based approach for multi-step forecasting.

Time Series

Learning Dynamical Systems from Noisy Data with Inverse-Explicit Integrators

1 code implementation • 6 Jun 2023 • Håkon Noren, Sølve Eidnes, Elena Celledoni

We introduce the mean inverse integrator (MII), a novel approach to increase the accuracy when training neural networks to approximate vector fields of dynamical systems from noisy data.

Pseudo-Hamiltonian system identification

2 code implementations • 9 May 2023 • Sigurd Holmsen, Sølve Eidnes, Signe Riemer-Sørensen

Identifying the underlying dynamics of physical systems can be challenging when only provided with observational data.

Pseudo-Hamiltonian neural networks for learning partial differential equations

2 code implementations • 27 Apr 2023 • Sølve Eidnes, Kjetil Olsen Lye

Pseudo-Hamiltonian neural networks (PHNN) were recently introduced for learning dynamical systems that can be modelled by ordinary differential equations.

Pseudo-Hamiltonian Neural Networks with State-Dependent External Forces

2 code implementations • 6 Jun 2022 • Sølve Eidnes, Alexander J. Stasik, Camilla Sterud, Eivind Bøhn, Signe Riemer-Sørensen

Hybrid machine learning based on Hamiltonian formulations has recently been successfully demonstrated for simple mechanical systems, both energy conserving and not energy conserving.