Presented By O'Reilly and Cloudera
December 5-6, 2016: Training
December 6–8, 2016: Tutorials & Conference

Deep learning with TensorFlow

Wolff Dobson (Google)
1:30pm–5:00pm Tuesday, December 6, 2016
Chat, machine learning, and AI
Location: 310/311 Level: Intermediate
Average rating: ****.
(4.71, 7 ratings)

Prerequisite Knowledge

  • Basic familiarity with Python
  • An understanding of machine-learning basics (useful but not required)

Materials or downloads needed in advance

What you'll learn

  • Gain hands-on experience with TensorFlow and deep learning
  • Learn how to build and deploy simple and complex models with TensorFlow


Wolff Dobson walks you through training and deploying a machine-learning system using TensorFlow, a popular open source library, and demonstrates how to build machine-learning systems from simple classifiers to complex image-based models.

Wolff begins by building a simple classifier in TensorFlow before introducing deep learning by training a complex model in TensorFlow. By comparing the results of the two models, you’ll gain insight into deep learning and learn how it can be applied to complex problems in science and industry. Wolff concludes with a hands-on demonstration of deploying a model in production using TensorFlow Serving, a high-performance open source system designed for serving machine-learned models.

Photo of Wolff Dobson

Wolff Dobson


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.