PuSH - Publikationsserver des Helmholtz Zentrums München

Heumos, L. ; Ehmele, P.* ; Kuhn Cuellar, L.* ; Menden, K.* ; Miller, E.* ; Lemke, S.* ; Gabernet, G.* ; Nahnsen, S.*

mlf-core: A framework for deterministic machine learning.

Bioinformatics 39:8 (2023)
DOI PMC
Creative Commons Lizenzvertrag
MOTIVATION: Machine learning has shown extensive growth in recent years and is now routinely applied to sensitive areas. To allow appropriate verification of predictive models before deployment, models must be deterministic. Solely fixing all random seeds is not sufficient for deterministic machine learning, as major machine learning libraries default to the usage of nondeterministic algorithms based on atomic operations. RESULTS: Various machine learning libraries released deterministic counterparts to the nondeterministic algorithms. We evaluated the effect of these algorithms on determinism and runtime. Based on these results, we formulated a set of requirements for deterministic machine learning and developed a new software solution, the mlf-core ecosystem, which aids machine learning projects to meet and keep these requirements. We applied mlf-core to develop deterministic models in various biomedical fields including a single-cell autoencoder with TensorFlow, a PyTorch-based U-Net model for liver-tumor segmentation in computed tomography scans, and a liver cancer classifier based on gene expression profiles with XGBoost. AVAILABILITY AND IMPLEMENTATION: The complete data together with the implementations of the mlf-core ecosystem and use case models are available at https://github.com/mlf-core.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
Schlagwörter Reproducibility
ISSN (print) / ISBN 1367-4803
Zeitschrift Bioinformatics
Quellenangaben Band: 39, Heft: 4, Seiten: , Artikelnummer: 8 Supplement: ,
Verlag Oxford University Press
Verlagsort Oxford
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Computational Biology (ICB)
Lung Health and Immunity (LHI)
Förderungen Project "ZEISS-Certifications and Foundations of Safe Machine Learning Systems in Healthcare" from the Carl Zeiss foundation
Bundesministerium fur Bildung und Forschung de. NBI Cloud
DFG im Rahmen der Exzellenzstrategie des Bundes und derLa nder
Deutsche Forschungs Gemeinschaft