Learning deep learning (project 4, language translation)

27 sec read

In this project, I built a neural network for machine translation (English -> French).  I built and trained a sequence to sequence model on a dataset of English and French sentences that can translate new sentences from English to French. The model was trained on my own laptop with a Nvidia M1200 GPU. In the end, we reached ~95% accuracy. And here is an example of the translation:

Input

English Words: [‘he’, ‘saw’, ‘a’, ‘old’, ‘yellow’, ‘truck’, ‘.’]

Prediction

French Words: [‘il’, ‘a’, ‘vu’, ‘un’, ‘vieux’, ‘camion’, ‘jaune’, ‘.’, ‘<EOS>’]

As I do not know French, I checked Google Translate and it looks like the translation is pretty good.

The full project with code can be found here:
dlnd_language_translation.html

Stork API, a single line becomes a list of…

I want to show a list of my own publications on my webpage, is there an easy way to do so? Yes, Stork API,...
Xu Cui
26 sec read

Deep learning training speed with 1080 Ti and M1200

I compared the speed of Nvidia’s 1080 Ti on a desktop (Intel i5-3470 CPU, 3.2G Hz, 32G memory) and NVIDIA Quadro M1200 w/4GB GDDR5,...
Xu Cui
1 min read

Leave a Reply

Your email address will not be published. Required fields are marked *