Beta. Content is under active construction and has not been peer-reviewed. Report errors on
GitHub
.
Disclaimer
Theorem
Path
Curriculum
Paths
Demos
Diagnostic
Search
Quiz Hub
/
Variational Autoencoders
Variational Autoencoders
4 questions
Difficulty 4-6
View topic
Intermediate
0 / 4
4 intermediate
Adapts to your performance
1 / 4
intermediate (4/10)
state theorem
A Variational Autoencoder (VAE) combines an encoder, decoder, and a probabilistic latent space. What does the encoder output?
Hide and think first
A.
A single deterministic vector in latent space, identical to what a plain autoencoder produces
B.
A discrete categorical distribution over latent tokens, similar to VQ-VAE's quantized codebook
C.
Parameters of a distribution over the latent (typically mean and variance of a Gaussian), from which
z
is sampled
D.
A full reconstruction of the input at the latent layer, skipping the decoder
Submit Answer