VAE vs plain autoencoder — the key advantages.
mediumAnswer
- (1) Probabilistic latent → generative (sample z ~ p(z), decode → new x).
- (2) Regularized latent space by KL to prior → smooth interpolation, meaningful arithmetic.
- (3) Calibrated uncertainty.
- Weaknesses: VAE samples are typically blurrier than GAN samples (mean-of-modes issue), latent may collapse (posterior collapse), harder to train.
- Modern hybrid: VQ-VAE, β-VAE, hierarchical VAE (NVAE) address these.
Check yourself — multiple choice
- Same as AE
- VAE: probabilistic latent → generative + smooth interpolation + regularized; blurrier samples than GAN; posterior collapse; VQ-VAE / β-VAE / NVAE variants
- Random
- No advantage
VAE: generative + smooth latent + regularized; blurry samples + posterior collapse.
#representation-learning#deep-learning
Practise Unsupervised Learning
214 interview questions in this topic.