logoalt Hacker News

anon291 • today at 6:26 PM • 0 replies • view on HN

Training means we take the mathematical expression corresponding to the entire model, use differentiation rules to generate partial derivatives according to a user-specified loss function (not part of inference), and then apply the gradients from the calculated differentials using a learning rate.

In this case, they just ask the model what the weights ought to be.