Zero to ML hero with TensorFlow 2.0





Who is this presentation for?
- Software developers and business and technical decision makers
Level
Description
Get a programmer’s perspective on machine learning with Laurence Moroney, from the basics all the way up to building complex computer vision scenarios using convolutional neural networks and natural language processing with recurrent neural networks.
The tutorial is light on math and theory and heavy on code. You’ll start by learning the concepts of training versus programming, creating a very simple example where a neural network is trained to recognize patterns. This extends into computer vision with a scenario where you train a neural network to recognize items of clothing and branch into more complex images to learn how convolutions can be used to extract features in images so you can identify a cat by its ears or a horse by its snout.
You’ll then switch gears and look into some natural language processing, learning how to tokenize words, train neural networks to classify sentences in context, and maybe even do some basic text generation of your own. This will equip you with an understanding of how neural networks, machine learning, and deep learning are a new paradigm to open up new scenarios for you to build against.
Prerequisite knowledge
- A basic understanding of programming, particularly in Python
Materials or downloads needed in advance
- A laptop with a browser installed
What you'll learn
- Understand how ML works—in particular, how programming it works with TensorFlow

Laurence Moroney
Laurence Moroney is a developer advocate on the Google Brain team at Google, working on TensorFlow and machine learning. He’s the author of dozens of programming books, including several best sellers, and a regular speaker on the Google circuit. When not Googling, he’s also a published novelist, comic book writer, and screenwriter.
Comments on this page are now closed.
Presented by
Diamond Sponsor
Elite Sponsors
Gold Sponsor
Supporting Sponsors
Premier Exhibitors
Exhibitors
Innovators
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
sponsorships@oreilly.com
For information on exhibiting or sponsoring a conference
pr@oreilly.com
For media/analyst press inquires
Comments
Here’s the slides from the session: https://storage.cloud.google.com/laurencemoroney-blog.appspot.com/tfw-training.zip
Thanks much this excellent presentation.
Armed with the knowledge gained I feel confident to head back to the office as an ML Hero!
Hi Veronica:
I think you’re the perfect audience for this. The idea is to help people who know some coding, but who don’t get ML yet to make the transition. We’ll start very basic with a ‘Hello World’ of ML, and gradually build up to more complex stuff like Computer Vision, showing how the same patterns of code are used throughout.
Hope that helps! :)
Hi Laurence,
I am interested in this presentation, seems amazing. However I am not sure it is for me. I am analyst and work with lots of data, have basic knowledge of Python use a lot of SQL and want to get more involved in ML. Do you think I’ll be able to follow up on this training and gain knowledge I can apply to my work?
Thank you,
Veronica
Hi Thomas — I will be high level with Keras, and a lot of introductory material very similar to what’s on Coursera.
I’ve taken Moroney’s TF course on Coursera, however the course was focused mainly on the Keras API for TF. Will this tutorial be focused explicitly on the TF library or on high level wrappers like Keras?