AI engineering glossary · Generative media multimodal
What is score-based generative model?
Score-based generative model: A generative approach that learns the score, the gradient of the log probability density of the data, and generates samples by following this gradient from noise with Langevin-style dynamics. It is mathematically linked to diffusion models, which can be seen as a discretised version of the same idea.
Score-based generative model: an example
A network estimates which direction makes a noisy pixel grid more like real photographs, and sampling repeatedly nudges the grid in that direction.
Related terms
- Score matching
- Diffusion model
- Energy-based model
More Generative media multimodal terms
- Short-time Fourier transform
- SigLIP
- Speaker diarisation
- Speaker embedding
- Spectrogram
- Speech-to-speech translation
- SSIM
- Stable Diffusion
Where you learn it
Score-based generative model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.