In-Person Training

Machine Learning + TensorFlow

Learn how to use TensorFlow to run your machine learning workflow

November 1 & 2, 2016

9:00am – 5:00pm PDT

Mission Bay Conference Center, San Francisco, CA

See ticket options

Course limited to 30 people. Sign up before it sells out!

TensorFlow, Google’s open source tensor computation framework, provides a powerful platform on which to build deep learning models. Join Google’s Eli Bixby and Amy Unruh for a two-day, hands-on, in-depth exploration of TensorFlow. You’ll come away with a solid understanding of TensorFlow and the ability to successfully run a machine learning workflow.

What you’ll learn—and how you can apply it

By the end of this live, hands-on course, you’ll understand:

  • The basic concepts in TensorFlow and how to apply them
  • The popular deep learning models in a variety of domains
  • How TensorFlow allows you to run machine learning workloads in production at scale

And you’ll be able to:

  • Utilize model wrappers provided with TensorFlow to build and iterate on complex models with only a few lines of code
  • Define models that efficiently distribute work across devices and machines
  • Run distributed models in the Google Cloud Machine Learning API, or in your own Kubernetes cluster
  • Export models and serving inference requests efficiently

This course is for you because…

  • You are a data scientist looking to expand your machine learning expertise
  • You are a machine learning expert looking to become familiar with TensorFlow
  • You are a data scientist or machine learning expert interested in learning how to run ML workloads at scale in production


  • Basic knowledge of Python
  • Experience with any/all of the following packages preferred: pandas, NumPy, SciPy, scikit-learn, Theano, Caffe, Torch, Spark, and Apache Beam

About your instructors

Amy Unruh

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.

Eli Bixby

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.

Course outline

  • Day One Morning
  • Basic Tensorflow Concepts:
    • Graphs
    • Sessions
    • Ops
    • Tensors
  • Deep learning refresher:
    • Loss functions
    • Optimizers
    • Basic model architectures
  • Day One Afternoon
  • Build Basic ML Models:
    • word2vec
    • MNist
  • Day Two Morning
  • Advanced TensorFlow concepts:
    • Supervisors
    • Coordinators
    • Distributed Tensorflow
    • TFRecords
    • Custom Operations
  • Advanced ML Concepts:
    • Transfer Learning
    • Generative Models
  • Day Two Afternoon
  • Build advance models:
    • LSTM for text generation
    • Criteo CTR prediction


The course will be held at: Mission Bay Conference Center at UCSF, 1675 Owens Street, San Francisco, California

Lunch will be provided.

Travel discounts

Rental Car Discounts


If you need a rental car while attending the conference, you may go to the Hertz Interactive Reservation System to receive the special O’Reilly discount on rental cars for the conference. Or call Hertz Reservations at (800) 654-3131 and mention code #01XY0041.

United Airline Discount


To receive your 3%–10% Discount on United Airlines flights to our event, you can book online at and provide discount Code ZVUR591372. Or, for a $25 service fee you can call United Meetings at (800) 426-1122 where a ticketing agent can help you by phone.

Group tickets

Working as a team? Learn as a team.

Taking this course as a team ensures that everyone is on the same page and understands both the immediate and long-term and immediate goals of your project. Exploring new ideas and collaborating on exercises together is a great team-building experience; everyone on your team will have the opportunity to ask questions, discuss use cases, and learn from other participants.

For group tickets and enterprise licensing, please contact

Code of Conduct

All participants must follow our Code of Conduct, the core of which is this: an O’Reilly events should be a safe and productive environment for everyone. Read more

O’Reilly Media, Inc. assumes no responsibility or liability for the facilities or services provided by the vendors and suppliers. Anyone attending this conference releases O’Reilly from any and all claims that may arise out of attending at this conference.

Thanks for signing up!
We protect your privacy.
Thanks for signing up!
We protect your privacy.