> For the complete documentation index, see [llms.txt](https://dashpay.gitbook.io/roboflux-whitepaper/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://dashpay.gitbook.io/roboflux-whitepaper/5.-anomaly-detection-subsystem/5.2-online-learning-adaptation.md).

# 5.2 Online Learning Adaptation

To accommodate dynamic operational baselines, the ADS employs an online learning paradigm where model weights are periodically fine-tuned via streaming stochastic gradient descent (SGD) on recently observed data.

Features include:

* **Concept Drift Detection:** Employs Page-Hinkley test for detecting distributional shifts in telemetry.
* **Incremental Backpropagation:** Applies adaptive mini-batch updates without full retraining.