Published on

Text and RNNs


Sam Witteveen and I recently started the TensorFlow and Deep Learning Singapore group on MeetUp, and the forth MeetUp was again hosted by Google.

This 1 hour talk (which was intended to last 45 minutes) included a TensorFlow version of the Upper Case NER notebook that was already in the deep-learning-workshop repo - and I have to admit, the overall example is again better in the TF version, because I teased out some details along the way, including adding a full data downloader notebook that enables the models to be used stand-alone.

The presentation also includes links to the relevant code at suitable points.

Presentation Screenshot

If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.

Presentation Content Example

The presentation was kindly recorded by


By the way, the deep-learning-workshop repo is undergoing some major refactoring. The aim is to make the individual examples work in a stand-alone fashion (downloading the necessary dependencies) while the assembled-into-a-VM still works with everything pre-loaded.

That means that downloading an individual notebook and stepping through it should just work. If it doesn't please let me know, and I'll prioritorize fixing it.