Train a model with TensorFlow and run it in the browser
Please join us for an introductory TensorFlow workshop, taught at the beginner level. In this half-day session, we’ll introduce TensorFlow, then work through several simple exercises using tf.keras, TensorFlow’s latest and easiest to use high-level API. We will train a few models in Python, then work through each step needed to run a model in the browser (entirely client side, and interactively!) using TensorFlow.js. Next, we will serve our model using a REST API. The tutorial assumes basic prior machine learning experience, but is taught at the beginner level, and you can probably follow along even if you’re entirely new to the field. We’ll be available afterwards for discussions and deeper technical content if you have anything you’d like to chat about. There is no software to install, we’ll do everything in Colab.
Josh Gordon works on the TensorFlow team at Google, and teaches Deep Learning at Columbia University. He has over a decade of machine learning experience to share. You can find him on Twitter at @random_forests.
Robert Crowe is a recovering data scientist and TensorFlow addict. Robert has a passion for helping developers quickly learn what they need to be productive. He’s used TensorFlow since the very early days and is excited about how it’s evolving quickly to become even better than it already is. Before moving to data science Robert led software engineering teams for both large and small companies, always focusing on clean, elegant solutions to well-defined needs. In his spare time, Robert surfs, sails, and raises a family.
Tue 28 May Times are displayed in time zone: (GMT-04:00) Eastern Time (US & Canada) change
|14:00 - 17:30|