Generative Models

A generative model learns how data is distributed so it can produce new examples. Many approaches use a latent variable and generate outputs through sampling.

Japanese terms

1. Generative model — 生成せいせいモデル: A model that learns a data distribution and can produce new samples resembling its training data.
2. Latent variable — 潜在変数せんざいへんすう: An unobserved variable used by a model to explain patterns in observed data.
3. Sampling — サンプリング: The process of drawing examples from a probability distribution or generative model.

Related topics

Foundation models can provide broadly capable generative systems, while multimodal AI extends generation across text, images, audio, and video.