Function parametrization: Difference between revisions

No edit summary
Line 28: Line 28:
== Alternatives ==
== Alternatives ==


* [[Bayesian data analysis]], which allows non-Gaussian error distributions.
* [[Bayesian data analysis]], which allows non-Gaussian error distributions. A very powerful method but not fast due to the need for maximization (not suited for real-time applications).
* Neural networks.
* Neural networks. Like with FP, most of the computational effort is concentrated in an analysis phase (network ''training''), before the actual application to data. Therefore, this methis is fast and suited for real-time applications.


== References ==
== References ==
<references />
<references />