Autoencoder

A parameterized function composed of interconnected units organized in layers with nonlinear activations.

Autoencoder using probabilistic latent variables and KL regularization.

Two-network setup where generator fools a discriminator.

Generator produces limited variety of outputs.

Exact likelihood generative models using invertible transforms.

Diffusion model trained to remove noise step by step.

Learns the score (∇ log p(x)) for generative sampling.

Controls amount of noise added at each diffusion step.

Diffusion performed in latent space for efficiency.