Building Blocks of Machine Learning at LEGO with Francesc Joan Riera - #533
Published:Nov 4, 2021 17:05
•1 min read
•Practical AI
Analysis
This article from Practical AI discusses the application of machine learning at The LEGO Group, focusing on content moderation and user engagement. It highlights the unique challenges of content moderation for a children's audience, including the need for heightened scrutiny. The conversation explores the technical aspects of LEGO's ML infrastructure, such as their feature store, the role of human oversight, the team's skill sets, the use of MLflow for experimentation, and the adoption of AWS for serverless computing. The article provides insights into the practical implementation of ML in a real-world context.
Key Takeaways
- •LEGO utilizes machine learning for content moderation and user engagement.
- •The article highlights the importance of human-in-the-loop systems for content moderation, especially for children's products.
- •The discussion covers technical aspects like feature stores, MLflow, and AWS serverless adoption.
Reference
“We explore the ML infrastructure at LEGO, specifically around two use cases, content moderation and user engagement.”