Jump to content

Generative adversarial networks

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

Generative adversarial networks

A machine learning framework in which two neural net­works contest with each other in the form of a zero-sum game, where one agent’s gain is another agent’s loss. A GAN learns to generate new data with the same statistics as the training set.


Source: NIST AI 100-2e2025 | Category: