O'Reilly logo
live online training icon Live Online training

Introduction to TensorFlow

Learn the basics of machine learning, deep learning using TensorFlow

Michael Li
Dana Mastropole
Robert Schroll

Get started with machine learning using TensorFlow, the popular open source machine-learning software developed by Google’s Brain team.

In this online course, you’ll learn core concepts in machine learning and TensorFlow with a focus on neural networks. You'll gain experience working with TensorFlow’s collection of visualization tools, including building and launching graphs in TensorFlow and using TensorBoard to visualize workflow and evaluate model performance. The instructors use notebooks with interactive code segments to guide you as you apply machine-learning concepts and build algorithms that make predictions using real-world datasets. By the end of the course, you’ll know how and when to use TensorFlow in your own applications.

What you'll learn-and how you can apply it

By the end of this live, online course, you’ll understand:

  • The basics of machine learning, neural networks, deep learning, and artificial intelligence
  • What TensorFlow is and what applications it is good for

And you’ll be able to:

  • Create statistical models for classification and regression using TensorFlow
  • Evaluate the benefits and disadvantages of using TensorFlow over other machine-learning software

This training course is for you because...

  • You’re a software engineer or programmer with a background in Python, and you want to develop a basic understanding of machine learning.
  • You have experience modeling or a background in data science, and you’d like to learn TensorFlow.
  • You’re in a nontechnical role, and you’d like to more effectively communicate about TensorFlow and neural networks with the engineers and data scientists in your company.


  • A basic understanding of Python and modeling
  • Familiarity with matrices and linear algebra

Materials and downloads needed:

  • A machine with TensorFlow installed and set up prior to the training

About your instructor

  • Michael is the CEO and Founder of The Data Incubator. While working as Head Data Scientist at Foursquare, he discovered that his favorite part of the job was teaching and mentoring smart people about data science, which lead to the creation of The Data Incubator. He also has worked as a quant (D.E. Shaw, J.P. Morgan), and a rocket scientist (NASA). He completed his PhD at Princeton as a Hertz fellow and read Part III Maths at Cambridge as a Marshall scholar.

    From helping hiring companies find qualified candidates for data driven roles to providing hands-on corporate trainings, Michael has enjoyed building his startup that lets him focus on what he loves.

  • Dana Mastropole is a Data Scientist in Residence at the Data Incubator. She studied physics as an undergraduate at Georgetown University and received her master’s degree in physical oceanography from MIT. She also completed MIT’s Kaufman teaching certificate program andtaught elementary school science prior to joining the Data Incubator team.

  • Robert Schroll is a Data Scientist in Residence at The Data Incubator and has been a key contributor to a variety of open source software development and data science projects. He obtained his Ph.D. in computational physics from the University of Chicago before completing postdocs in Amherst, Massachusetts, and Santiago, Chile. There, he realized that the favorite parts of his job were teaching and analyzing data. He made the switch to data science and hasbeen teaching at the Data Incubator for the past six months.


The timeframes are only estimates and may vary according to how the class is progressing

Day 1: Introduction to TensorFlow

What are machine learning and TensorFlow? (20 minutes)

TensorFlow basics: Data types and iterative algorithms (20 minutes)

Building and launching graphs in TensorFlow (20 minutes)

Break (10 minutes)
Implementing Newton’s method of root finding (20 minutes)

Using the TensorBoard (20 minutes)

Q&A (20 minutes)

Assignment: Continue working on in-class exercise

Day 2: Introduction to machine learning

Machine learning basics: Linear regression (20 minutes)

Machine learning basics: Logistic regression (20 minutes)

Building a model to classify flowers in the iris dataset (20 minutes)

Break (10 minutes)

Basic neural networks (20 minutes)

Neural networks in TensorFlow (20 minutes)

Q&A (20 minutes)

Assignment: Continue working on in-class exercise

Day 3: Introduction to deep learning

Deep learning and deep neural networks (20 minutes)

Training a deep neural network to classify handwritten digits (20 minutes)

Basic versus convolutional neural networks: Performance evaluation (20 minutes)

Break (10 minutes)

Convolutional neural networks (20 minutes)

Generative networks (20 minutes)

Q&A (20 minutes)