Skip to content
ml-recall

#score-function

4 questions from Diffusion Models, Policy Gradient & Actor-Critic

Timed test

4 questions · 4 min · score and explanations at the end

Take a test
Q 1 / 4Score 0 / 0

Question 1: Single choice

easyAI-checkedDiffusion Models

Diffusion models work with the score of a density, s(x)=∇xlog⁡p(x)\mathbf{s}(\mathbf{x}) = \nabla_{\mathbf{x}} \log p(\mathbf{x}). For a single Gaussian p=N(μ,σ2I)p = \mathcal{N}(\boldsymbol\mu, \sigma^2 I), what do the direction and the length of the score tell you at a point x\mathbf{x}?

Choose one option