Systems · AI Systems · Core
Variational Autoencoder
A VAE is a probabilistic autoencoder: the encoder outputs a distribution q(z|x), the decoder p(x|z), and training maximizes an ELBO with a KL term that keeps the latent well-behaved.
Definition
A VAE is a probabilistic autoencoder: the encoder outputs a distribution q(z|x), the decoder p(x|z), and training maximizes an ELBO with a KL term that keeps the latent well-behaved.
RelatedDiffusion ModelGenerative Adversarial NetworkActivation FunctionAdam OptimizerAgent WorkflowAttention MechanismAutoencoderBackpropagationBatch NormalizationBeam SearchBERTByte Pair EncodingChain of ThoughtCLIP