Put open source to work
July 16–17, 2018: Training & Tutorials
July 18–19, 2018: Conference
Portland, OR

Machine learning with TensorFlow: From linear algebra to neural networks (Day 2)

Rich Ott (The Pragmatic Institute)
Location: F150
Tags: tensorflow

Who is this presentation for?

  • You are an engineer or programmer with a background in Python, and you want to develop a basic understanding of machine learning.
  • You have experience modeling or have a background in data science, and you would like to learn TensorFlow.

Prerequisite knowledge

  • A working knowledge of Python
  • Familiarity with matrices and linear algebra

What you'll learn

  • Understand TensorFlow's capabilities
  • Learn machine learning basic concepts


Incorporating machine learning capabilities into software or apps is quickly becoming a necessity rather than a “nice to have” feature. Open source machine learning framework TensorFlow is becoming an industry standard.

Rich Ott leads you through two days of intensive learning that includes a review of linear algebra essential to machine learning, an introduction to TensorFlow, and a dive into neural networks. You’ll master simple machine learning models such as classification and regression models, construct and launch graphs in TensorFlow by using TensorBoard to visualize workflow and build and test models in TensorFlow using real-world data. You’ll leave with both a theoretical and practical understanding of the algorithms behind machine learning and be ready to incorporate them into your next project.

The class will be taught using TensorFlow’s Python interface.


Day 2

  • Machine learning
  • Basic neural networks
  • Deep neural networks


  • Multidimensional linear regression
  • Tuning hyperparameters and visualizing the weight matrix
  • Build an Iris classifier
  • Adding neurons and layers to a neural network
  • Implementing early stopping
  • Exploring activation functions, dropout, and learning rates
Photo of Rich Ott

Rich Ott

The Pragmatic Institute

Richard Ott obtained his PhD in particle physics from the Massachusetts Institute of Technology, followed by postdoctoral research at the University of California, Davis. He then decided to work in industry, taking a role as a data scientist and software engineer at Verizon for two years. When the opportunity to combine his interest in data with his love of teaching arose at The Data Incubator, he joined and has been teaching there ever since.