News for hackers. Stuff that matters.
Re:Deep Learning and Free Software by nlowell on Thursday July 26, 2018 @11:28AM (#17618199)
I think distributing the weights will give you guaranteed reproducibility. If your users intend on retraining the network, another idea would be to set performance expectations on a validation set within ballpark. So you could tell them, "we got 90% accuracy on this dataset, if you re-train and get below 80 you've probably made a mistake somewhere." The scary thing to me would be the very small test cases where maybe different trained neural nets end up having a lot of variance because there is barely more than noise to learn.
Re:Deep Learning and Free Software by JanisL on Saturday July 28, 2018 @01:06AM (#17631645)
Distributing the weights seems to be the safest method, something I'll have to look into a bit more. It's a bit disturbing that training with the same data and same parameters could lead to different weights and therefore different accuracies but it's better to know that this is the case than not.