Skip to content
ml-recall

#ddpm

8 questions from Diffusion Models

Timed test

8 questions · 8 min · score and explanations at the end

Take a test
Q 1 / 8Score 0 / 0

Question 1: Short answer

mediumAI-checkedDiffusion Models

A DDPM forward process adds noise with q(xt∣xt−1)=N(αt xt−1,βtI)q(x_t \mid x_{t-1}) = \mathcal{N}(\sqrt{\alpha_t}\,x_{t-1}, \beta_t I), where αt=1−βt\alpha_t = 1 - \beta_t. For a scalar x0=2x_0 = 2 and the schedule β1,β2,β3=0.1,0.2,0.3\beta_1, \beta_2, \beta_3 = 0.1, 0.2, 0.3, what is the mean of x3x_3 given x0x_0?

a number, 2 decimals