17–19 October 2016: Conference & Tutorials
19–20 October 2016: Training
London, UK

Diving into machine learning through TensorFlow

Amy Unruh (Google), Eli Bixby (Google)
9:30–13:00 Wednesday, 19/10/2016
Open data & data science
Location: Sandringham Level: Intermediate
Average rating: *....
(1.67, 3 ratings)

Prerequisite knowledge

  • A basic understanding of Python
  • A familiarity with basic machine-learning concepts (useful but not required)

Materials or downloads needed in advance

What you'll learn

  • Understand the basics of TensorFlow concepts
  • Learn how to use TensorFlow to define neural net graphs, train them (including how to do cloud-based distributed training), and use the trained models for prediction

Description

TensorFlow is an open source software library from Google for numerical computation using data flow graphs. It provides a flexible platform for defining and running machine-learning algorithms and is particularly well suited for building deep neural networks.

Amy Unruh and Eli Bixby offer practical, hands-on experience with TensorFlow. Amy and Eli start by providing some background and motivation for problems in machine learning and introduce some core TensorFlow concepts. Then, they dive into a deeper exploration of TensorFlow by building and training several different neural nets.

Topics include:

  • How to use TensorFlow’s powerful libraries to define and train NN graphs
  • How to use TensorFlow with Jupyter notebooks
  • Using the TFLearn (Scikit Flow) library
  • How to do distributed training of TensorFlow models
  • How to scalably serve learned TensorFlow models and use trained models for prediction on a range of devices
Photo of Amy Unruh

Amy Unruh

Google

Amy Unruh is a developer programs engineer at Google for the Google Cloud Platform, where she works with TensorFlow as well as many other Cloud Platform technologies. Amy has a PhD in CS/AI, has worked in academia, at several startups, and in industrial R&D, and has published a book on App Engine.

Photo of Eli Bixby

Eli Bixby

Google

Eli Bixby is a developer programs engineer at Google currently developing on Google Cloud Platform’s DevOps distributed systems, machine-learning, and big data offerings. He joined Google as a developer programs engineer. Previously, Eli dabbled in several research areas, with papers in biophysics, algorithmic game theory, and most recently computational biology.

Comments on this page are now closed.

Comments

Alexey Vyskubov
19/10/2016 13:57 BST

Let me quote the description: “practical, hands-on experience with TensorFlow”. What we’ve got was an extended presentation, with hands-on part practically missing (well, we were asked to add a couple of lines to existing file once). Frankly speaking, I’d rather spend my time reading documentation and playing with code examples instead of looking at code snippets on slides. Not well prepared (or even “not at all prepared”) as a tutorial.