Presented By O’Reilly and Cloudera
Make Data Work
21–22 May 2018: Training
22–24 May 2018: Tutorials & Conference
London, UK

In-Person Training
Machine learning with TensorFlow

Dana Mastropole (The Data Incubator)
Monday, 21 May & Tuesday, 22 May, 9:00 - 17:00
Location: Capital Suite 17

Participants should plan to attend both days of this 2-day training course. Platinum and Training passes do not include access to tutorials on Tuesday.

The TensorFlow library enables the use of data flow 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. Dana Mastropole details TensorFlow's capabilities through its Python interface.

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

  • Understand TensorFlow's capabilities
  • Explore TFLearn, a high-level deep learning library built on TensorFlow

Prerequisites:

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

Attendees should have experience coding in Python and familiarity with matrix algebra. Having a computer that can connect to the internet is a necessity. No downloads or software installations are required, but it is recommended that attendees have either Chrome or Firefox installed on their computers.

The TensorFlow library enables the use of data flow 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. Dana Mastropole details TensorFlow’s capabilities through its Python interface, moving from building machine learning algorithms piece by piece to using the higher-level abstractions provided by TensorFlow. You’ll use this knowledge to build machine learning models on real-world data.

You’ll be provisioned a cloud instance with TensorFlow as a part of this course.

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 Dana Mastropole

Dana Mastropole is a data scientist in residence at the Data Incubator and contributes to curriculum development and instruction. Previously, Dana taught elementary school science after completing MIT’s Kaufman teaching certificate program. She studied physics as an undergraduate student at Georgetown University and holds a master’s in physical oceanography from MIT.

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 Dana Mastropole
Dana Mastropole | DATA SCIENTIST IN RESIDENCE
19/04/2018 21:45 BST

Hello,

We will train machine learning models using TensorFlow’s Python API, so having some experience coding in Python is required. In order to understand the implementation and theory behind these models, a basic understanding of matrix algebra, calculus, and statistics is also helpful. For example, it is assumed that attendees know how to multiply two matrices, how to take a derivative, and what a probability distribution is. The models we will cover include linear regression, logistic regression, and neural networks.

Best,
Dana

Maciej Dzieżyc | SOFTWARE ENGINEER
17/04/2018 18:35 BST

Hello,

what kind of “Familiarity with Python, matrices, modeling, and statistics” is required to take this training? Especially is it required to have knowledge about topics that will be discussed (e.g. convolutional neural networks)?

Best regards

Picture of Dana Mastropole
Dana Mastropole | DATA SCIENTIST IN RESIDENCE
4/04/2018 21:30 BST

Hi Daniele,

I’ll answer your questions in order:

- The training will cover the same material (with a few updates/modifications) as last year’s TensorFlow workshop at London’s Strata Data conference.

- The exercises will be done on CPUs only.

- We will be using jupyter notebooks as the teaching platform.

Daniele Bonacorsi | RESEARCHER
28/03/2018 14:43 BST

Dear Dana,

a couple of questions if I may:

- in what (if any) is this training different in content or more/less advanced than the same one from DataIncubator that was held at last year’s Strata Data conference in London?

- will TF-based training be done on GPUs in the exercises, or only on CPUs?

- will you be using python jupiter notebooks as the main teaching platform, or what else?

Thanks!

Picture of Dana Mastropole
Dana Mastropole | DATA SCIENTIST IN RESIDENCE
9/03/2018 19:31 GMT

Hi Lise, the prerequisites are the following:
- Python
- Familiarity with matrices
- Familiarity with modeling
- Familiarity with statistics

Lise-Marie Motet
9/03/2018 6:13 GMT

Hi Dana
What are the prerequisites for the training?
Thanks

Picture of Dana Mastropole
Dana Mastropole | DATA SCIENTIST IN RESIDENCE
26/01/2018 21:31 GMT

Yes, the training will be on your personal computer. We recommend that you have either chrome or firefox.

Camillo C |
26/01/2018 9:10 GMT

Hello, is the training to be made with personal laptops ? if it is, is there a suggested preconfiguration ?