Course Outline


  • Why Neural Machine Translation?
  • Borrowing from image recognition techniques

Overview of the Torch and Caffe2 projects

Overview of a Convolutional Neural Machine Translation model

  • Convolutional Sequence to Sequence Learning
  • Convolutional Encoder Model for Neural Machine Translation
  • Standard LSTM-based model

Overview of training approaches

  • About GPUs and CPUs
  • Fast beam search generation

Installation and setup

Evaluating pre-trained models

Preprocessing your data

Training the model


Converting a trained model to use CPU-only operations

Joining to the community

Closing remarks


  • Some programming experience is helpful
  • Basic understanding of neural networks
  • Experience using the command line


  • Localization specialists with a technical background
  • Global content managers
  • Localization engineers
  • Software developers in charge of implementing global content solutions
  7 Hours

Related Courses

Related Categories