Sep 9–12, 2019

Using Keras to classify text with LSTMs and other ML techniques

Lukas Biewald (CrowdFlower)
9:00am12:30pm Tuesday, September 10, 2019
Models and Methods
Location: 230 C

Who is this presentation for?

Machine Learning Engineer



Prerequisite knowledge

  • Familiar with Python.
  • Some experience with ML but not necessarily on text.

Materials or downloads needed in advance

  • Only a laptop with Chrome installed
  • Everything will be hosted on a Jupyter hub in a web browser to avoid installation problems. Though if you really want to configure things locally, install requirements.txt or follow the README.

What you'll learn

  • Text handing with scikit learn.
  • Building LSTMs/GRUs.
  • Introduction to Keras.


We will build and improve a sentiment classifier on text data. We will start with scikit learn and naive bayes and continuously improve the model. I will introduce Keras and then apply word embeddings and CNNs. Finally, we will build various types of LSTMs and GRUs.

This class is extremely hands-on but every attendee will be given a Jupyter hub instance set up with a cloud GPU to follow along.

Photo of Lukas Biewald

Lukas Biewald


Lukas Biewald is the founder of Weights and Biases. Before that he was the founder of CrowdFlower,a machine learning data labeling company acquired by Appen for 300 million dollars.. He was featured on Inc. magazine’s 30 under 30 list. Lukas holds a BS in mathematics and an MS in computer science from Stanford. He is also an expert Go player.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

Contact us

For conference registration information and customer service

For more information on community discounts and trade opportunities with O’Reilly conferences

For information on exhibiting or sponsoring a conference

Contact list

View a complete list of O'Reilly AI contacts