2019/03/12 by Tom Diethe, Tom Borchert, Diethe, Tom +8 · 18 citations
Computer Science · Mathematics · #Anomaly Detection Techniques and Applications #Architecture #Artificial intelligence #Computer science #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Outlier #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1903.05202
published in arXiv (Cornell University) (Cornell University) · Presented at the NeurIPS 2018 workshop on Continual Learning https://sites.google.com/view/continual2018/home
openalex publication_date 2019/03/12 · arxiv created 2019/03/18 · arxiv updated 2019/03/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives. In environments where data evolves, we need architectures that manage Machine Learning (ML) models in production, adapt to shifting data distributions, cope with outliers, retrain when necessary, and adapt to new tasks. This represents continual AutoML or Automatically Adaptive Machine Learning. We describe the challenges and proposes a reference architecture.