scientific article; zbMATH DE number 3911505
[For the entire collection see Zbl 0564.00022.] Most classification methods are static, in the sense that the complete set of data \(X_ R\) is already closed when the problem is posed. Optimization is then the most appropriate concept to be applied. It is nevertheless useful in many situations to look at classification of data arriving sequentially as an uninterrupted flow. Then the problem consists in assigning a class to a just observed element, and to extract the information it carries about X. Sequential classification falls then into the field of sequential estimation of a partition of X.
- Self-learning pattern classification using a sequential clustering technique
- Sequential non-stationary dynamic classification with sparse feedback
- Using generative models to combine static and sequential features for classification
- Unsupervised process monitoring and fault diagnosis with machine learning methods
- Health monitoring with learning methods
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3687529)