Presented By
O’Reilly + Cloudera
Make Data Work
29 April–2 May 2019
London, UK

TensorFlow for everyone

Wolff Dobson (Google, Inc.)
14:5515:35 Wednesday, 1 May 2019
Data Science, Machine Learning & AI, Expo Hall
Location: Expo Hall (Capital Hall N24)
Secondary topics:  Deep Learning
Average rating: ***..
(3.83, 6 ratings)

Who is this presentation for?

  • New and experienced AI developers who want to learn TensorFlow best practices

Level

Beginner

Prerequisite knowledge

  • Familiarity with Python
  • A basic understanding of machine learning concepts, such as framing problems, data, models, training, and inference

What you'll learn

  • Gain an overview of TensorFlow best practices
  • See what's new in 2.0 and how it can help you get great results

Description

TensorFlow—the most popular open source platform for machine learning—is transitioning to 2.0 in early 2019. Join Wolff Dobson to get the very latest updates straight from the Google Brain team.

Whether you’re a beginner or are migrating from 1.x to 2.0, you’ll learn the best ways to set up your model, feed your data to it, and distribute it for fast training. You’ll also discover how TensorFlow has been recently upgraded to be more intuitive. Along the way, you’ll see how to use TensorFlow’s new eager-first execution and its revised, easier-to-use distribution strategy library, along with other new features.

Topics include:

  • Building machine learning models with high level APIs
  • Feeding data efficiently to your model
  • Distributing your training to many machines
Photo of Wolff Dobson

Wolff Dobson

Google, Inc.

Wolff Dobson is a developer programs engineer at Google specializing in machine learning and games. Previously, he worked as a game developer, where his projects included writing AI for the NBA 2K series and helping design the Wii Motion Plus. Wolff holds a PhD in artificial intelligence from Northwestern University.