News for hackers. Stuff that matters.
Re:Alice's adventures in a differentiable wonderland by esafak on Tuesday April 30, 2024 @03:30PM (#40215221)
functions, which you can compose to increase their expressiveness, and run gradient descent on to train.

The success of deep learning is basically attributable to composable (expressive), differentiable (learnable) functions. The "deep" moniker alludes to the compositionality.

There are no comments on this comment yet.