Is there any fundamental difference between learning algorithms e.g. variants of PAC which have continuous access to examples on which to train (i.e. these are obtained as the algorithm runs, when called for), versus those which get a lump of samples from the start which they have to utilise?

  • $\begingroup$ What counts as a fundamental difference? You have already identified one difference: whether they get continuous access to examples or not. I'm not sure what you're looking for in an answer. Can you ask a more focused question? My experience is that asking "is there a fundamental difference between X and Y" is often not the best fit for our site format; if you understand X and Y, you should be able to figure that out, and if you don't, then it might be more useful to others in the future to ask a specific question about some aspect of X or Y that you're unsure of. $\endgroup$
    – D.W.
    Jun 16 at 4:44

Your Answer

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

Browse other questions tagged or ask your own question.