Introduction to TensorFlow

Robert Schroll (The Data Incubator)

9:00am—5:00pm Monday, October 28—Tuesday, October 29

Location: Room 204

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, ideal architecture for implementing neural networks. Robert Schroll introduces TensorFlow's capabilities in Python, moving from building machine learning algorithms piece by piece to using the Keras API provided by TensorFlow with several hands-on applications.

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

Understand what machine learning, neural networks, deep learning, and artificial intelligence are
Discover what TensorFlow is and what applications it's good for
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 with a background in Python, and you wish to develop an understanding of machine learning.
You have experience modeling or have a background in data science, and you would like to learn TensorFlow and deep learning.
You're in a nontechnical role, and you would like to more effectively communicate with the engineers and data scientists in your company about TensorFlow and neural networks.

Level

Intermediate

Prerequisites:

Familiarity with Python, matrices, modeling, and statistics

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

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

Guoqiong Song |

11/01/2019 8:06am PDT

Hi Robert,
Could you please post the slides and a link? Many thanks

Tarek Khorshed | Lead Technology Architect

09/10/2019 1:59am PDT

Hi Robert,
I’ve been working with Keras for over 2 years and I have very good knowledge of building and training CNNs using Keras. My objective is to have a more in-depth knowledge of Tensorflow 2.0 and its APIs. Will this be covered in the training?

Robert Schroll | Data Scientist in Residence

08/23/2019 8:35am PDT

Hi Dan! We will definitely be introducing the Keras API, and a lot of our code uses Keras. We’re working on upgrading the curriculum to TF2, and I’m pretty confident we’ll have it ready to go by October.

Dan R | Psychiatrist, University Lecturer

08/10/2019 7:12am PDT

Hi, I’m interested in the Introduction to Tensorflow training session. I have had a little experience with Keras and would prefer to use the Keras interface to tensorflow as much as possible. Will you be using the Keras implementation in Tensorflow in this session? Also, Tensorflow 2 should be in RC or even released by the conference. I’d prefer to use Tensorflow 2 in the training session. Will you be using Tensorflow 2?
Many thanks,
Daniel

Scott Johnson | Principle Software Engineer

07/26/2019 3:46am PDT

Hi Robert. By “glance at some introductory materials” I presume you mean look through some getting started info at https://www.tensorflow.org/tutorials/. Yes? I will certainly do this. Thank you for your response!

Robert Schroll | Data Scientist in Residence

07/25/2019 4:06am PDT

Hi Scott! In the first session, we introduce some of the basic operations in TensorFlow. If you a quick glance at some introductory materials before the course, I’m sure you’ll be able to catch up quickly before we get into any of the material focused on deep learning or neural networks.

Scott Johnson | Principle Software Engineer

07/20/2019 8:51am PDT

I’m registered for the 2-day Intro to TensorFlow training, but I might not be able to arrive until Monday morning. Do you think that if I arrive approx. an hour late (10am) will I miss so much that I am unable to catch up over the first break?
Thanks.