52. VQ-VAE
Learning objectives
- Introduce VQ-VAE
Variational Auto-Encoders
Variational Auto-Encoders
In AI architecture, variational autoencoders simulate the latent space (between the encoder and decoder)—usually with a mixture of Gaussian functions—to maximize the ELBO (evidence lower bound)
VAE Gaussians
without
without VAE
- image source: Jeff Orchard
with
with VAE
- image source: Jeff Orchard
VQ-VAE
VQ-VAE
Vector quantized variational autoencoders (VQ-VAE) utilize an discrete embedding space
- for example: 32x32 embedding space of vectors
VQ-VAE
52. VQ-VAE