Generative AI Flashcards
1
Q
Diffusion Models
A
Markov Chain: Models sequence of noise distributions
Generates by de-noising
Forward diffusion: Introduce noise (gaussian) into the input until it becomes completely noisy. Markov Chain, doesn’t require training
Backward diffusion: Denoising process learned with NN
2
Q
GANs
A
3
Q
VAEs
A
4
Q
What is diffusion in physics?
A
Movement of particles from high concentration to low concentration
Increases entropy
5
Q
Markov Chain
A
A stochastic model describing a sequence of events where the probability of each event depends only onto the previous state
6
Q
Monte Carlo Simulations
A
Involve repeated random samplings
7
Q
Markov Chain Monte Carlo Sampling
A
