Building Blocks of Machine Learning at LEGO with Francesc Joan Riera - #533

Topics covered
Popular Clips
Episode Highlights
Team Structure
LEGO's data and AI teams are structured to leverage a diverse range of skills, ensuring robust machine learning solutions. explains that their team includes full-stack developers, machine learning engineers, data scientists, and platform specialists, each contributing to different facets of their projects 1. This diversity allows them to tackle complex challenges, such as developing an engagement tool that uses image classifiers to recognize themes in user uploads. Initially, the tool struggled with accuracy, but the team's collaborative efforts led to improvements and successful user interaction 1.
We are very happy we have full stack developer in our team because he's a mastermind in doing our frontend tool.
---
This multidisciplinary approach is crucial for maintaining and enhancing LEGO's digital products, especially in areas like content moderation and user engagement.
Skill Diversity
The diversity of skills within LEGO's AI teams is a significant asset, enabling innovative solutions across various projects. highlights his journey from studying industrial electronics to becoming an applied machine learning engineer, illustrating the varied backgrounds that contribute to the team's success 2. This range of expertise supports projects like the automated engagement tool, which uses non-player characters (NPCs) to interact with users, enhancing their experience and satisfaction 3.
It's very fulfilling for us as well to see that the reactions are positive.
---
Such diversity not only fosters creativity but also ensures that LEGO can effectively address the unique challenges of their digital initiatives.
Related Episodes


Building AI Products with Hilary Mason - #11
Answers 383 questions

Data Science on AWS with Chris Fregly and Antje Barth - #490
Answers 383 questions

The Enterprise LLM Landscape with Atul Deo - 640
Answers 383 questions

Building LLM-Based Applications with Azure OpenAI with Jay Emery - 657
Answers 383 questions

Advancements in Machine Learning with Sergey Levine - #355
Answers 383 questions

Automated Machine Learning with Erez Barak - #323
Answers 383 questions

Machine Learning Commerce at Square with Marsal Gavalda - #384
Answers 383 questions

Buy AND Build for Production Machine Learning with Nir Bar-Lev - #488
Answers 383 questions

Machine Learning at GSK with Kim Branson - #536
Answers 383 questions

Deep Learning, Transformers, and the Consequences of Scale with Oriol Vinyals - #546
Answers 383 questions

Productive Machine Learning at LinkedIn with Bee-Chung Chen - TWiML Talk #200
Answers 383 questions

Interactive Machine Learning Systems with Alekh Agarwal - #17
Answers 383 questions

Quantum Machine Learning: The Next Frontier? - With Iordanis Kerenidis - #397
Answers 383 questions

Compositional ML and the Future of Software Development with Dillon Erb - #520
Answers 383 questions













