Put AI to Work
April 15-18, 2019
New York, NY

TensorFlow 2.0: Machine learning for you

Joshua Gordon (Google)
11:05am11:45am Wednesday, April 17, 2019
Implementing AI
Location: Rendezvous
Secondary topics:  Deep Learning and Machine Learning tools
Average rating: ****.
(4.83, 6 ratings)

Who is this presentation for?

  • Developers, software engineers, and decision makers

Level

Beginner

Prerequisite knowledge

  • Familiarity with TensorFlow and machine learning

What you'll learn

  • Learn the latest in TensorFlow for 2.0
  • Discover how to use TensorFlow like a pro
  • Understand the delta between 1.x and 2.0

Description

The TensorFlow team has recently released plans for TensorFlow 2.0. 2.0 is always-eager execution, which leads to many shifts in how you should expect to use TensorFlow, especially for how you interact with graphs. TensorFlow 2.0 is more object based, both around saving and optimization. As you create subfunctions, you can apply “@defun” decorators to accelerate them. @defun uses Autograph to allow you to place loops, subfunctions, and other Python structures on accelerators. This can lead to a flexible, easy-to-use Pythonic approach to building machine learning, all with the familiar scaling, performance, and distribution that you expect from TensorFlow.

Josh Gordon shares the very latest in TensorFlow, focusing on TensorFlow 2.0 and its easy-to-use eager execution. Josh also covers how to use TensorFlow’s revised high-level API and details pitfalls and tricks to get better performance on accelerator hardware.

Photo of Joshua Gordon

Joshua Gordon

Google

Josh Gordon is a developer advocate at Google AI and teaches applied deep learning at Columbia University and machine learning at Pace University. He has over a decade of machine learning experience to share. You can find him on Twitter as @random_forests.