✳flâneur — a map of the web's best reading

A ten-minute introduction to sequence-to-sequence learning in Keras

blog.keras.io · 2,457 words · saved by 1 readers

I see this question a lot -- how to implement RNN sequence-to-sequence learning in Keras? Here is a short introduction. Note that this post assumes that you already have some experience with recurrent networks and Keras. Sequence-to-sequence learning (Seq2Seq) is about training models to convert sequences from one domain (e.g. sentences in English) to sequences in another domain (e.g. the same sentences translated to French). This can be used for machine translation or for free-from question answering (generating a natural language answer given a natural language question) -- in general, it is applicable any time you need to generate text. There are multiple ways to handle this task, either using RNNs or using 1D convnets. Here we will focus on RNNs. When both input sequences and output sequences have the same length, you can implement such models simply with a Keras LSTM or GRU layer (or stack thereof). This is the case in this example script that shows how to teach a RNN to learn to

Note: this post is from 2017. See this tutorial for an up-to-date version of the code used here. I see this question a lot -- how to implement RNN sequence-to-sequence learning in Keras? Here is a short introduction. Note that this post assumes that you already have some experience with recurrent networks and Keras. What is sequence-to-sequence learning? Sequence-to-sequence learning (Seq2Seq) is about training models to convert sequences from one domain (e.g. sentences in English) to sequences in another domain (e.g. the same sentences translated to French). "the cat sat on the mat" -> [ Seq2

Explore this link on the map →

saved by

related reading