novelty detection

The process of determining whether a new (novel) example comes from the same distribution as the training set. In other words, after training on the training set, novelty detection determines whether a new example (during inference or during additional training) is an outlier. Contrast with outlier detection.

Practitioners refer to novelty detection when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.