The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Building Blocks of Machine Learning at LEGO with Francesc Joan Riera - #533
6 snips
Nov 4, 2021 
Francesc Joan Riera, an applied machine learning engineer at LEGO, dives into the intricacies of machine learning within the company. He discusses innovative content moderation techniques tailored for child safety. Riera also shares insights about integrating human feedback with algorithms and implementing a serverless A-B testing framework using AWS. He highlights the importance of efficient data management strategies and the evolution of machine learning infrastructure, ultimately aiming to enhance user engagement through theme detection in LEGO apps.
AI Snips
Chapters
Transcript
Episode notes
Lego Sorting Demo
- Francesc Joan Riera mentions a project to recover a Lego sorting demo from the internet.
- Lego aims to explore its potential as a product, aligning with their circular economy goals.
Lego's Content Moderation
- Lego uses ML for content moderation to protect children, prioritizing instant feedback.
- Pre-filtering rejects obvious violations, while approved content undergoes manual review.
Automated User Engagement
- Lego uses ML for user engagement by automatically identifying creation themes and having NPCs interact.
- This automation replaced manual engagement and increased user uploads and positive reactions.