This section outlines models that support online learning and out-of-core model updates. These models operate on and update in reaction to streaming data inputs, allowing for continuous learning and for models to be fit on data that would be too large to fit into memory.
Documentation is broken into the following sections:
- SGD - Stochastic Gradient Descent (SGD).
- Linear Regression - SGD based Linear Regression.
- Logistic Classification - SGD based Logistic Classification.
- Protected/Secure Updates - Outline of the operation of functionality used to ensure production models are not 'polluted' by unexpected data.
- Sequential K-Means - Sequential/Online K-Means.