top | item 46201394 (no title) moelf | 2 months ago you can always make a new vector that's orthogonal to all the ones currently used and see if the inclusion improves performance on your tasks discuss order hn newest scotty79|2 months ago > see if the inclusion improves performance on your tasksApparently it doesn't at least not in our models with our training applied to our tasks.So if we expand one of those 3 things and notice that 17-th vector makes a difference then we are having progress.
scotty79|2 months ago > see if the inclusion improves performance on your tasksApparently it doesn't at least not in our models with our training applied to our tasks.So if we expand one of those 3 things and notice that 17-th vector makes a difference then we are having progress.
scotty79|2 months ago
Apparently it doesn't at least not in our models with our training applied to our tasks.
So if we expand one of those 3 things and notice that 17-th vector makes a difference then we are having progress.