5,321
edits
(→L) |
(→E) |
||
Line 20: | Line 20: | ||
* Early stopping - a technique where you stop training once the validation loss begins increasing. This is not as popular these days with large models. | * Early stopping - a technique where you stop training once the validation loss begins increasing. This is not as popular these days with large models. | ||
* Early exitting - a technique to optimize neural network inference by routing features directly to an output head instead of through the entire model. | * Early exitting - a technique to optimize neural network inference by routing features directly to an output head instead of through the entire model. | ||
* Embedding - see latent code. This is a just a feature used to represent something. | |||
==F== | ==F== |