In this workshop we will go through classifying the language root of a name using a Deep Learning approach. We will train a character level RNN to process the name predict the root language. This workshop assumes no familiarity with Deep Learning, but does assume some familiarity with Python. If you are unfamiliar with python, ask a friend or just follow along!
This workshop is designed to be done in <2 hours with the programming necessary being done live by the presenter and the class following along.
This workshop is run in a Jupyter notebook. For minimal setup we will use Google Colab notebooks in the browser.
In the new notebook page for google colab, chose Github Repo and enter the url of this repository https://github.com/leobrowning92/char-rnn-workshop and select livecode_template.ipynb.
The workshop is adapted from the Pytorch NLP From Scratch: Classifying Names with a Character-Level RNN Tutorial. Changes have been made to work better with a live coded format.
Here are the public version of the slides that I use to explain various concepts throughtout