33 citations · 34 across the 6 of their papers we have counts for
6 papers
Measuring Deep Learning Performance - An Empirical Study of Performance Distributions Across Architectures and Tasks
Kevin L Coakley, Odd Erik Gundersen
Context: Non-determinism in deep learning algorithm design and implementation leads to performance variation, meaning model performance is not a single value, but rather a distribu…
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,…
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…
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…
Engaging with Researchers and Raising Awareness of FAIR and Open Science through the FAIR+ Implementation Survey Tool (FAIRIST)
Christine R. Kirkpatrick, Kevin L. Coakley, Julie Christopher +1
Six years after the seminal paper on FAIR was published, researchers still struggle to understand how to implement FAIR. For many researchers FAIR promises long-term benefits for n…
Sources of Irreproducibility in Machine Learning: A Review
Odd Erik Gundersen, Kevin Coakley, Christine Kirkpatrick +1
Background: Many published machine learning studies are irreproducible. Issues with methodology and not properly accounting for variation introduced by the algorithm themselves or…