News for hackers. Stuff that matters.
Re:Differences between the word2vec paper and its implementa... by Dylan16807 on Tuesday June 04, 2019 @07:30AM (#20093921)
For almost all ML training, it's straightforward to break it into a fixed number of chunks without race conditions.

That's if float rounding issues are even a big problem in the first place. If your results are within .1% over a few runs it's reproducible enough for most purposes.

There are no comments on this comment yet.