Autoencoder
Benjamin Lagrandeur
contributed
This wiki is incomplete.
Autoencoders are a type of artificial neural network which attempt to reconstruct data from a compressed reperesentation. An autoencoder consists of an encoder, a bottleneck, and a decoder. The encoder receives an input and compresses it into a dense representation in the bottleneck layer, which has fewer neurons than the input. The decoder takes the information from the bottleneck and attempts to reconstruct the input.
Section Heading
Add explanation that you think will be helpful to other members.
Cite as:
Autoencoder.
Brilliant.org.
Retrieved from
https://brilliant.org/wiki/autoencoder/