On Mon, Jan 21, 2002 at 04:57:21AM -0500, Chris Mesterharm wrote: > I was hoping someone could suggest an area within the Linux kernel > that could benefit from research in machine learning. Hmm. Kernels typically don't have much call for machine learning.. (The virtual memory system could certainly benefit from more informed guesses of which memory pages will be accessed soon..) I imagine you could also apply machine learning algorithms to the scheduler, though I think it would be rather specific to your training machines. (which might be your goal all the same..) Stephanie Forrest (sp?) has done some research into statistical measurements of what normal processes do, versus what malicious processes do; you may wish to read her papers. Cheers :) -- People who separate manpages from the programs they document would steal sheep. -- apologies to Goudy
Attachment:
pgp00024.pgp
Description: PGP signature
