Presented By O’Reilly and Intel AI
Put AI to work
Sep 4-5, 2018: Training
Sep 5-7, 2018: Tutorials & Conference
San Francisco, CA

In-Person Training
Deep learning with TensorFlow

Robert Schroll (The Data Incubator)
9:00am-5:00pm
Tuesday, September 4 through Wednesday, September 5
Location: Continental 2 Level: Intermediate
Secondary topics:  Computer Vision, Deep Learning tools
Average rating: ****.
(4.00, 2 ratings)

Participants should plan to attend training courses on both Tuesday and Wednesday. To attend training courses, you must register for a Platinum or Training pass; does not include access to tutorials on Wednesday.

The TensorFlow library provides for the use of dataflow graphs for numerical computations, with automatic parallelization across several CPUs or GPUs. This architecture makes it ideal for implementing neural networks and other machine learning algorithms. Robert Schroll offers an overview of the TensorFlow graph using its Python API.

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

  • Understand TensorFlow’s strengths for machine learning and how TensorFlow can help with AI problems like object recognition and text processing
  • Learn how to build a basic computation within TensorFlow, using Python

Prerequisites:

  • Familiarity with Python, matrices, modeling, and statistics
  • No experience with TensorFlow required

Hardware and/or installation requirements:

  • A laptop (You'll be provisioned with a cloud instance with TensorFlow.)

Many of the deep learning algorithms used in AI applications are powered by large matrix operations. TensorFlow provides dataflow graphs for such operations, allowing algorithms to be easily parallelized across multiple processors or machines. This makes TensorFlow an ideal environment for implementing neural networks and other deep learning algorithms.

Robert Schroll offers an overview of the TensorFlow graph using its Python API. You’ll start with simple machine learning algorithms and move on to implementing neural networks, including convolutional neural networks to provide object recognition for machine vision, recurrent neural networks, including long short-term memory architectures, that allow the comprehension of time series and language, and generative networks, which give AI applications the ability to create output. Along the way, Robert covers several real-world deep learning applications, including machine vision, text processing, and generative networks.

Outline

Day 1:

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

Day 2:

  • Deep neural networks
  • Variational auto-encoders
  • Convolutional neural networks
  • Adversarial noise
  • DeepDream
  • Recurrent neural networks

About your instructor

Photo of Robert Schroll

Robert Schroll is a data scientist in residence at the Data Incubator. Previously, he held postdocs in Amherst, Massachusetts, and Santiago, Chile, where he realized that his favorite parts of his job were teaching and analyzing data. He made the switch to data science and has been at the Data Incubator since. Robert holds a PhD in physics from the University of Chicago.

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

J. Joshua Thomas |
09/11/2018 12:44am PDT

Hi, I did not attend the training. However, i have seen this wonderful opportunity. Any materials will be shared? from this workshop. i really appreciate.

Chandra Subramanian | SVP - ANALYTIC MANAGER
08/29/2018 9:51am PDT

I am contemplating changing my registration to attend this training session instead of BigDL training. What is the format and content of Day 2? Will Day 2 be hand-on and include actual use cases, and corresponding datasets, for each algorithm listed above? Please clarify. thanks!