3 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.AI2023
Examining the Effect of Implementation Factors on Deep Learning Reproducibility
Kevin Coakley, Christine R. Kirkpatrick, Odd Erik Gundersen
Reproducing published deep learning papers to validate their conclusions can be difficult due to sources of irreproducibility. We investigate the impact that implementation factors…