Pre‐training: Difference between revisions
Appearance
imported>Unknown user No edit summary |
imported>Unknown user No edit summary |
| (2 intermediate revisions by the same user not shown) | |
(No difference)
| |
Latest revision as of 00:24, 20 January 2026
Pre‐training
In machine learning, a training step that trains a general‐purpose model (sometimes called a foundation model) on publicly‐available data. Pre‐training is often followed by fine‐tuning to equip the model with task‐specific information.
Source: NIST SP 800-226 | Category: