# Ubisoft La Forge produces a data-driven physics simulation based on machine learning

*Source* · `src-ubisoft-2019-data-driven-physics` · status: **n/a**

| field | value |
|---|---|
| kind | Technical report / blog |
| authors | Ubisoft La Forge |
| venue | Ubisoft news |
| date | 2019-09-19 |
| url | https://www.ubisoft.com/en-us/studio/laforge/news/1Dp7nj7RdnpgPAbftcRu7V/a-datadriven-physics-simulation-based-on-machine-learning |
| accessed | 2026-10-24 |
| notes | Studio summary of Holden et al. 2019: runs 300 to 5000 times faster than conventional physics simulation at small additional memory cost. |

## Backlinks (computed)

**cited by:** [Subspace neural physics and learned deformers](../technique/subspace-neural-physics.md)

## Citation

Ubisoft La Forge (2019-09-19). *Ubisoft La Forge produces a data-driven physics simulation based on machine learning*. Ubisoft news https://www.ubisoft.com/en-us/studio/laforge/news/1Dp7nj7RdnpgPAbftcRu7V/a-datadriven-physics-simulation-based-on-machine-learning

---
Provenance: created in run `2026-10-24-techniques-sim-math`.