On Tue, Jul 3, 2018 at 2:18 AM, jimlux <[email protected]> wrote: > they're using Support Vector Machines and Machine Learning (how sexy! how > fashionable!) >
This approach has been done before, I wonder why it's not mentioned in their literature survey. The papers below have more details. [1] Sirdey, R. & Maurice, F. "A linear programming approach to highly precise clock synchronization over a packet network" F. 4OR (2008) 6: 393. https://doi.org/10.1007/s10288-007-0060-6 [2] D. E. Pinkovich and N. Shimkin, "Clock synchronization using maximal margin estimation" 2011 19th Mediterranean Conference on Control & Automation (MED), Corfu, 2011, pp. 1182-1187. https://doi.org/10.1109/MED.2011.5983128 _______________________________________________ time-nuts mailing list -- [email protected] To unsubscribe, go to http://lists.febo.com/mailman/listinfo/time-nuts_lists.febo.com and follow the instructions there.
