activity
20242026
collaborators

6 papers

cs.AI2026

The Shift Toward Open and Reproducible AI Research

Kevin L Coakley, Thijs Snelleman, Holger Hoos +1

The reproducibility crisis has directed the AI research community toward improving documentation practices. Several studies have identified methodological issues, and in response,…

cs.LG2026

Learning to be Reproducible: Custom Loss Design for Robust Neural Networks

Waqas Ahmed, Sheeba Samuel, Kevin Coakley +2

To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent a…

cs.CY2025

Automated Reproducibility Has a Problem Statement Problem

Thijs Snelleman, Peter Lundestad Lawrence, Holger H. Hoos +1

Background. Reproducibility is essential to the scientific method, but reproduction is often a laborious task. Recent works have attempted to automate this process and relieve rese…

physics.comp-ph2025

Examining the robustness of Physics-Informed Neural Networks to noise for Inverse Problems

Aleksandra Jekic, Afroditi Natsaridou, Signe Riemer-Sørensen +2

Approximating solutions to partial differential equations (PDEs) is fundamental for the modeling of dynamical systems in science and engineering. Physics-informed neural networks (…

cs.LG2025

EXPRTS: Exploring and Probing the Robustness of Time Series Forecasting Models

Håkon Hanisch Kjærnli, Lluis Mas-Ribas, Hans Jakob Håland +4

When deploying time series forecasting models based on machine learning to real world settings, one often encounter situations where the data distribution drifts. Such drifts expos…

cs.AI2024

The Unreasonable Effectiveness of Open Science in AI: A Replication Study

Odd Erik Gundersen, Odd Cappelen, Martin Mølnå +1

A reproducibility crisis has been reported in science, but the extent to which it affects AI research is not yet fully understood. Therefore, we performed a systematic replication…