the
∞
.ai
Search
/
Concepts
trail ·
0 nodes
Every concept
Generative
8 concepts, 8 reviewed and merged.
Architecture
GAN
Two networks against each other: one makes samples, the other tries to tell them from real data, and the first…
verified
Normalizing Flow
Build a generator out of invertible steps.
verified
Evaluation
Likelihood vs Sample Quality
A model can assign excellent probability to the data and produce terrible samples, or produce beautiful samples while…
verified
Inference
Sampling Steps
Every iterative generator trades quality against how many times it runs the network.
verified
Objectives
Flow Matching
Diffusion learns to undo noise step by step.
verified
Score Matching
You can describe a distribution by where its density is going up rather than by the density itself — the gradient of…
verified
Regimes
Mode Collapse
A generator discovers that one convincing output fools the discriminator and stops producing anything else.
verified
Schedules
Denoising Schedule
A diffusion model is trained across a range of noise levels, and how that range is traversed at sampling time is a…
verified