> For the complete documentation index, see [llms.txt](https://seattle-university.gitbook.io/sdgne/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://seattle-university.gitbook.io/sdgne/auto-encoder.md).

# Auto Encoder

Autoencoders are a class of neural networks designed for unsupervised learning and representing features in a smaller space. They consist of an encoder and a decoder, intending to learn the input data's compressed representation (encoding).  We leverage this architecture to generate synthetic data.

SDGnE package contains three Autoencoder models:

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td></td><td>Balanced Autoencoder</td><td></td><td><a href="/sdgne/auto-encoder/balanced-autoencoder.md">Balanced Autoencoder</a></td></tr><tr><td></td><td>Heavy Decoder Autoencoder</td><td></td><td><a href="/sdgne/auto-encoder/heavy-decoder-autoencoder.md">Heavy Decoder Autoencoder</a></td></tr><tr><td></td><td>Single Encoder Autoencoder</td><td></td><td><a href="/sdgne/auto-encoder/single-encoder-autoencoder.md">Single Encoder Autoencoder</a></td></tr></tbody></table>