TechRxiv
Reliable_AI_through_SVDD_and_rule_extraction.pdf (4.94 MB)

Reliable AI through SVDD and rule extraction

Download (4.94 MB)
preprint
posted on 02.06.2021, 09:30 by Alberto CarlevaroAlberto Carlevaro

The proposed paper addresses how Support Vector Data Description (SVDD) can be used to detect safety regions with zero statistical error. It provides a detailed methodology for the applicability of SVDD in real-life applications, such as Vehicle Platooning, by addressing common machine learning problems such as parameter tuning and handling large data sets. Also, intelligible analytics for knowledge extraction with rules is presented: it is targeted to understand safety regions of system parameters. Results are shown by feeding data through simulation to the train of different rule extraction mechanisms.

History

Email Address of Submitting Author

alberto.carlevaro@edu.unige.it

ORCID of Submitting Author

https://orcid.org/0000-0002-7206-5511

Submitting Author's Institution

University of Genoa

Submitting Author's Country

Italy

Usage metrics

Licence

Exports