Machine Learning

How to Develop an Encoder-Decoder Model for Sequence-to-Sequence Prediction in Keras

Last Updated on August 27, 2020

The encoder-decoder model provides a pattern for using recurrent neural networks to address challenging sequence-to-sequence prediction problems such as machine translation.

Encoder-decoder models can be developed in the Keras Python deep learning library and an example of a neural machine translation system developed with this model has been described on the Keras blog, with sample code distributed with the Keras project.

This example can provide the basis for developing encoder-decoder LSTM models for your own sequence-to-sequence prediction problems.

In this tutorial, you will discover how to develop a sophisticated encoder-decoder recurrent neural network for sequence-to-sequence prediction problems with Keras.

After completing this tutorial, you will know:

  • How to correctly define a sophisticated encoder-decoder model in Keras for sequence-to-sequence prediction.
  • How to define a contrived yet scalable sequence-to-sequence prediction problem that you can use to evaluate the encoder-decoder LSTM model.
  • How to apply the encoder-decoder LSTM model in Keras to address the scalable integer sequence-to-sequence prediction problem.

Kick-start your project with my new book Long Short-Term Memory Networks With Python, including step-by-step tutorials and the Python source code files for all examples.

Let’s get started.