✳flâneur — a map of the web's best reading
ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias
proceedings.mlr.press · 771 words · saved by 1 readers
This site last compiled Mon, 15 Apr 2024 06:31:27 +0000
ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias Yupu Lu, Shijie Lin, Guanqi Chen, Jia Pan Proceedings of the 39th International Conference on Machine Learning , PMLR 162:14384-14397, 2022. Abstract Deep learning models are able to approximate one specific dynamical system but struggle at learning generalisable dynamics, where dynamical systems obey the same laws of physics but contain different numbers of elements (e.g., double- and triple-pendulum systems). To relieve this issue, we proposed the Modular Lagrangian Network (ModLaNet), a structural neural n
Explore this link on the map →saved by
related reading
- Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamicsproceedings.mlr.press
- Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
- pdfopenreview.net
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- On neural scaling and the quanta hypothesisericjmichaud.com
- Just Ask for Generalization | Eric Jangevjang.com
- Natural Intelligencegreydanus.github.io
- Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
- Investigating the learning coefficient of modular addition: hackathon project — LessWronglesswrong.com
- NL.pdfabehrouz.github.io
- [2503.02113] Deep Learning is Not So Mysterious or Differentarxiv.org
- Deep learning as program synthesis — LessWronglesswrong.com