News for hackers. Stuff that matters.
Re:Show HN: I invented a new generative model and got accept... by ProjectArcturis on Saturday October 11, 2025 @10:34PM (#45554663)
This is probably an uninformed question, but why are you comparing layers' output to ground truth? Isn't the point that ground truth is unknown?
Re:Show HN: I invented a new generative model and got accept... by diyer22 on Sunday October 12, 2025 @01:57AM (#45555645)
During neural network training, the ground truth (GT) must be known to compute the loss.

In DDN, the GT is only used to calculate the loss and guide sampling; it never becomes an input to the model.