Establishing Machine Learning Operations for Continual Learning in Computing Clusters: A Framework for Monitoring and Optimizing Cluster Behavior

@article{mcspadden2025establishing,
  title = {Establishing Machine Learning Operations for Continual Learning in Computing Clusters: A Framework for Monitoring and Optimizing Cluster Behavior},
  author = {Diana McSpadden and Mark Jones and A. Mohammed and Bryan Hess and M. Schram},
  year = {2025},
  journal = {IEEE Software},
  doi = {10.1109/MS.2024.3424256},
  url = {https://doi.org/10.1109/MS.2024.3424256},
}