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 Content is under active construction and has not been peer-reviewed.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
/
Autoencoders
Autoencoders
3 questions
Difficulty 2-4
View topic
Foundation
0 / 3
1 foundation
2 intermediate
Adapts to your performance
1 / 3
foundation (2/10)
conceptual
An autoencoder is a neural network that maps an input
x
to itself through a bottleneck representation. What is its primary use?
Hide and think first
A.
Unsupervised representation learning, where the bottleneck layer captures a compact summary of the input distribution
B.
Data augmentation, where the reconstruction output replaces the input with a noisy version for training
C.
Supervised classification, where the bottleneck layer learns class-discriminative features for downstream prediction
D.
Loss function design, where the autoencoder's reconstruction error is used as the loss in any supervised network
Submit Answer