AI Blog

AI Blog

by Michele Laurelli

Back to Glossary

Encoder-Decoder

/ɪnˈkoʊdər dɪˈkoʊdər/
Architecture
Definition

An architecture where an encoder processes input into a representation and a decoder generates output from it.

Encoder-decoder architectures are used for sequence-to-sequence tasks. The encoder compresses input into a context vector, the decoder generates output. Common in machine translation and summarization.

Examples

1

Seq2Seq for translation

2

Transformer encoder-decoder

3

VAE (Variational Autoencoder)

Related Terms

Transformer

A neural network architecture based entirely on attention mechanisms, without recurrent or convolutional layers.

Attention Mechanism

A technique allowing models to focus on specific parts of the input when producing output.

Michele Laurelli - AI Research & Engineering