Sep 23–26, 2019

Machine learning from scratch in TensorFlow

Dylan Bargteil (The Data Incubator)
9:00am—5:00pm Monday, September 23—Tuesday, September 24
Location: 1E 07
Average rating: *....
(1.50, 2 ratings)

Participants should plan to attend both days of training course. Note: to attend training courses, you must be registered for a Platinum or Training pass; does not include access to tutorials on Tuesday.

The TensorFlow library provides for the use of computational graphs with automatic parallelization across resources. This architecture is ideal for implementing neural networks. Dylan Bargteil explores TensorFlow's capabilities in Python, demonstrating how to build machine learning algorithms piece by piece and how to use TensorFlow's Keras API with several hands-on applications.

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

  • Understand machine learning, neural networks, deep learning, and artificial intelligence basic concepts
  • Learn what TensorFlow is and what applications it's good for
  • Discover how to create deep learning models for classification and regression using TensorFlow
  • Evaluate the benefits and disadvantages of using TensorFlow over other machine learning software

Who is this presentation for?

  • You're a software engineer or programmer who wants to develop a basic understanding of machine learning.
  • You have experience modeling or have a background in data science, and you want to learn TensorFlow.

Level

Intermediate

Prerequisites:

  • A working knowledge of Python
  • Familiarity with matrices, modeling, and statistics

Hardware and/or installation requirements:

  • A WiFi-enabled laptop (You'll be given a cloud instance with TensorFlow.)

Outline

Day 1

  • Introduction to TensorFlow
  • Iterative algorithms
  • Machine learning
  • Basic neural networks

Day 2

  • Deep neural networks
  • Variational autoencoders
  • Convolutional neural networks
  • Adversarial noise
  • DeepDream
  • Recurrent neural networks

About your instructor

Photo of Dylan Bargteil

Dylan Bargteil is a data scientist in residence at the Data Incubator, where he works on research-guided curriculum development and instruction. Previously, he worked with deep learning models to assist surgical robots and was a research and teaching assistant at the University of Maryland, where he developed a new introductory physics curriculum and pedagogy in partnership with the Howard Hughes Medical Institute (HHMI). Dylan studied physics and math at the University of Maryland and holds a PhD in physics from New York University.

Twitter for thedatainc

Conference registration

Get the Platinum pass or the Training pass to add this course to your package.

Comments on this page are now closed.

Comments

Picture of Dylan Bargteil
Dylan Bargteil | Data Scientist in Residence
08/21/2019 4:41pm EDT

We will be using TensorFlow 2.0, and we will make use of the Keras API for building and training neural networks.

PyTorch is a different deep learning framework that is distinct from TensorFlow and will not be covered (though comparisons are made where relevant).

Nishit Ajwaliya | Enterprise Data Architect
08/01/2019 1:22pm EDT

I am also interested about the version.

Also I would like to know if we will be using KERAS or PYTORCH for model training?

Myrto Miltiadous | Sr Data Scientist
05/23/2019 5:01am EDT

Is it going to be TensorFlow 2.0?

    Contact us

    confreg@oreilly.com

    For conference registration information and customer service

    partners@oreilly.com

    For more information on community discounts and trade opportunities with O’Reilly conferences

    strataconf@oreilly.com

    For information on exhibiting or sponsoring a conference

    pr@oreilly.com

    For media/analyst press inquires