We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control
deepmind.google·6d ago
AI Engineering
MIT Technology Review·Jun 11·5 min read
Inside soccer’s data renaissance
TL;DR
Soccer teams lacked data-driven insights to optimize strategies and player evaluations. Jesse Davis's team at KU Leuven developed tree ensemble models to analyze over 1.4 million passes and 60,000 throw-ins.
✦ Why It Matters
Engineers and researchers can leverage data analytics to uncover unconventional strategies in sports and other domains.
Key Takeaways
- Explore machine learning applications in sports analytics.
- Utilize open-source tools like VAEP for performance assessment.
- Analyze game strategies using large datasets for better insights.
- Collaborate with data teams to standardize and improve data collection.
How It Works
The lab uses tree ensemble models to analyze soccer tactics, simulating various game scenarios to quantify the effectiveness of strategies like kicking the ball out of bounds. By processing extensive datasets, they can identify hidden patterns and optimize decision-making in real-time.