autoencoder

Neural network that learns efficient data encoding in an unsupervised manner

EntityQ786435

Also known as autoencoders · AE

Subclass of: artificial neural network

Overview

From Wikipedia, the free encyclopedia · Read full article · Text CC BY-SA 4.0

An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data. An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction, to generate lower-dimensional embeddings for subsequent use by other machine learning algorithms.

Overview

All data

24 statements · 17% with external sources · numbers in brackets are citations

Has use: data compression
lossy compression
Different from: Autocoder
Facet of: unsupervised learning
deep learning
Significant person: Michal Valko
1
Sources
1.misovalko.github.io/Retrieved 2025-12-14
View statement on Wikidata ↗

On other databases

10 identifiers linking autoencoder across the web's reference databases

Data quality

statements

17%

externally sourced

Source last edited August 11, 2026. AIDB refreshes this page daily.

Suggest a fact or correction

Links

Use this data

curl https://aidb.si/api/v1/entities/Q786435

API docs, limits & keys

Cite this page

AIDB. (2026). autoencoder (Q786435). Retrieved from https://aidb.si/e/autoencoder-Q786435