Sequence-to-sequence neural networks

Introduction

  • language translation: inputs sequence in one language, output in another
  • speech traslation: input are audio samples, output is text transcription
  • video description: input video frames, output is caption
  • and many more…
Encoder-decoder neural network architecture for sequence-to-sequence learning. An input sequence Xi is encoded into a sequence vector Zi by the encoder. The decoder produces an output sequence Yi which is auto-regressive.

Recurrent neural network s2s

s2s neural network based on RNN encoder and decoder. An inputs sequence is input one symbol at a time to the encoder RNN network (blue) to produce a sequence vector Se. The decoder is auto-regressive and takes the previous decoder output and the Se to produce one output symbol at a time.

Attention

Neural attention is uses in s2s neural network to perform a weighted learned average of the input embeddings, so that the most accurate set of input symbols can be used to produce the proper output symbol.

Conclusions

About the author

Donations

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store