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.

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.

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