Presented By O'Reilly and Cloudera
Make Data Work
Dec 4–5, 2017: Training
Dec 5–7, 2017: Tutorials & Conference
Singapore

TensorFlow wide and deep: Data classification the easy way

Yufeng Guo (Google)
4:15pm4:55pm Wednesday, December 6, 2017

Who is this presentation for?

  • Developers interested in using machine learning

Prerequisite knowledge

  • A working knowledge of Python (e.g., basic data structures and manipulations, such as dicts, list comprehensions, class/method structures, etc.)

What you'll learn

  • Learn an approach to build a machine learning model using TensorFlow that combines the benefits of linear models with deep neural networks
  • Understand what is going on inside the "black box" of machine learning

Description

Deep learning has already revolutionized machine learning research, but it remains out of reach for many developers. However, tools already exist today that enable leading-edge machine learning for many problem domains. TensorFlow, an open source machine learning library with a full Python interface, has become the most popular machine learning library on GitHub, and the community around it is growing rapidly.

Yufeng Guo leads an adventure to build a machine learning model using TensorFlow that combines the benefits of linear models with deep neural networks. You’ll also learn what is happening under the hood and how to use this model for your own datasets. Yufeng walks you through a practical approach for doing ML on structured data, in the process, demystifying machine learning.

Note: This is not an introduction to machine learning; nor is it an introduction to TensorFlow.

Photo of Yufeng Guo

Yufeng Guo

Google

Yufeng Guo is a developer advocate for the Google Cloud Platform, where he is trying to make machine learning more understandable and usable for all. He enjoys hearing about new and interesting applications of machine learning, so be sure to share your use case with him on Twitter.