You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The state-of-the-art inspiration to estimate_delay is nicely condensed in the thesis of Jan Schumann-Bischoff which you can find here: https://d-nb.info/1116709740/34. Chapter 9 on the Shinriki oscillator has all the ingredients of a good benchmark for all of these delay, reconstruction and prediction methods. It also extends to state and parameter estimation for a system of three timeseries and 9 parameters.
In Julia, forward diff is considered efficient whereas backward diff may be more problematical.
In Julia, forward diff is considered efficient whereas backward diff may be more problematical.
Backwards diff is fine these days. It'll be nice to have Capstan.jl completed, but it's really not necessary and there's no need to avoid ReverseDiff.jl these days.
The state-of-the-art inspiration to estimate_delay is nicely condensed in the thesis of Jan Schumann-Bischoff which you can find here: https://d-nb.info/1116709740/34. Chapter 9 on the Shinriki oscillator has all the ingredients of a good benchmark for all of these delay, reconstruction and prediction methods. It also extends to state and parameter estimation for a system of three timeseries and 9 parameters.
In Julia, forward diff is considered efficient whereas backward diff may be more problematical.
Want to back this issue? Post a bounty on it! We accept bounties via Bountysource.
The text was updated successfully, but these errors were encountered: