GenAIWiki

machine-learning

generative-models

Models that can generate new data instances similar to the training data.

Expanded definition

Generative models learn to capture the underlying distribution of a dataset to create new instances that are indistinguishable from real data. They are extensively used in tasks like image generation, text synthesis, and more. A common misconception is that all generative models produce high-quality outputs; in practice, quality can vary significantly based on model architecture and training data diversity.

Related terms

Explore adjacent ideas in the knowledge graph.

Related

Comparisons, tools, and models that connect to this idea.