1
$\begingroup$

Are there any machine learning algorithms or algorithms categories which have predictable execution times (guaranteed minimal/maximal execution time e.g. when the algorithm is run on a single processor which is not loaded with other processing tasks) for predictions given any possible input making them suitable for the use in hard real time systems?

$\endgroup$
  • $\begingroup$ Afaik any ML method needs at least to read the data as input, so if there's no bound on the size of the data there can't be any bound on the execution time. $\endgroup$ – Erwan Dec 21 '19 at 1:23
1
$\begingroup$

making them suitable for the use in hard real time systems

Not sure what you mean by "hard" real time systems, but what you describe is basically the context of data streams. That is a whole branch with its own algorithms. Since you don't specify much, I leave the answer here, pointing out what kind of algorithms you should research.

Hope this helps!

$\endgroup$
  • $\begingroup$ Machine learning in the context of data streams is helpful to improve (decrease) minimal prediction execution time. However it is not neccessary for hard real time capable predictions. Hard real time requirements means in the toughest case that a too early as well as a too late prediction (too fast or too slow algorithm execution time) make the precition useless for the application context. Your hint is good but not what I'm looking for. $\endgroup$ – thinwybk Dec 21 '19 at 10:13
  • $\begingroup$ ... the prediction usually need to be fast but they do not necessarily have to. The important point for hard real time capable systems is the predictable and guaranteed minimal and maximal prediction execution time. $\endgroup$ – thinwybk Dec 21 '19 at 10:19
  • $\begingroup$ If you consider the computational complexity of some algorithms the ones whose O depend on constant values (e.g. number of features) should be the ones with most predictable prediction execution times. $\endgroup$ – thinwybk Dec 21 '19 at 10:24

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for?Browse other questions tagged or ask your own question.