Self-organizing networks for extracting jet features
Summary, in English
Self-organizing neural networks are briefly reviewed and compared with supervised learning algorithms like back-propagation. The power of self-organization networks is in their capability of displaying typical features in a transparent manner. This is successfully demonstrated with two applications from hadronic jet physics; hadronization model discrimination and separation of b, c and light quarks.
- Department of Astronomy and Theoretical Physics
Computer Physics Communications
- Subatomic Physics
- ISSN: 0010-4655