Jump to content

Pre‐training

From Hackerpedia
Revision as of 00:12, 15 January 2026 by imported>Unknown user
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Languages: English | Français

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: