Workshop / Overview

Ad blockers are the most popular browser extension category for all browsers.

While most of the time they work just fine, in some cases their reliance on human curated filter lists becomes a bottleneck in tackling specific websites. This is where machine learning comes to rescue.

We will talk about multiple approaches for using machine learning in content blocking world and build a sample ML-based filter to hide a specific kind of ads, which are not blockable otherwise. We will learn what kind of data is needed to train the model, train the model and deploy it into a browser extension using TensorFlow.js.

Workshop / Outcome

Participants will experience and end-to-end process from collecting the data using custom code, to training the model and then deploying it on the Web with TensorFlow.js. They will also learn state of the art technique for writing ML-based content filters for the Web. After the workshop participants should be able to write their own content filters for the Web.

Workshop / Difficulty

Intermediate level

Workshop / Prerequisites

  • Basic understanding Machine Learning, Python and JavaScript
  • A small dataset will be provided during workshop
  • Own laptop

Track / Co-organizers

Oleksandr Paraska


Vasily Kuznetsov

Developer, eyeo

Tudor Avram

Software Engineer, eyeo

Levan Tsinadze

Machine Learning Researcher, eyeo

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 Machine Learning with R

With Dirk Wulff, Markus Steiner & Michael Schulte-Mecklenbeck

09:00-17:00 January 25Foyer 6

Feature Engineering for Spatial Data Analysis

With Caio Miyashiro, Selim Onat & Eva Jaumann

09:00-17:00 January 25Foyer 1

AMLD / Global partners