Workshop / Overview

This full-day workshop (slides, code) will show you how to transform big data into a TensorFlow dataset and then use Keras to create linear, convolutional and recurrent prediction models.

We use Colab notebooks to inspect and transform the QuickDraw dataset and train and run the models.

ML knowledge is not strictly required for understanding the TensorFlow code, but we won't have time to explain ML theory during the workshop. If you're new to the field and want to prepare in advance, consider reading through some blog posts describing the network architectures that we will use (CNN1, CNN2, RNN), watching some Stanford lectures (CNN, RNN), and/or some videos about ML concepts from Google's ML crash course.

Workshop / Outcome

Participants will have a working skeleton for creating their own dataset to train and run models using TensorFlow.

Workshop / Difficulty

Beginner level

Workshop / Prerequisites

  • Python programming
  • Own laptop with a modern browser

Track / Co-organizers

Andreas Steiner

Software Engineer, Google

Ruslan Habalov

Security Engineer, Google

Megan Ruthven

Software Engineer, Google

AMLD EPFL 2020 / Workshops

A Conceptual Introduction to Reinforcement Learning

With Kevin Smeyers, Katrien Van Meulder & Bram Vandendriessche

09:00-12:30 January 251ABC

Applied ML with R

With Dirk Wulff, Markus Steiner & Michael Schulte-Mecklenbeck

09:00-17:00 January 25Foyer 6

Augmenting the Web browsing experience using machine learning

With Oleksandr Paraska, Vasily Kuznetsov, Tudor Avram & Levan Tsinadze

09:00-12:30 January 253A

AMLD / Global partners