machine-learning-physics

Layer 1 — Physics18 concepts in this subtree

ML-physics interface: neural-net wave-functions (Carleo); learning Hamiltonians; symbolic-regression; equivariant networks (Cohen-Welling); ML-accelerated lattice-QCD; differentiable physics; Hamiltonian-NN; data-driven turbulence.

Carleo neural-net wave functions
Symbolic regression for physics laws
Equivariant neural networks (Cohen-Welling)
Hamiltonian + Lagrangian neural networks
Differentiable physics engines
ML-accelerated lattice QCD
Physics-informed neural networks (PINN)
Quantum machine learning (parameterised quantum circuits)
Turbulence ML models
Auto-discovery of conservation laws
Variational autoencoder for physics
Graph neural networks for molecular dynamics
NN potentials (Behler-Parrinello 2007)
AlphaFold 2 (Jumper 2021)
Neural ODE (Chen 2018)
PINN (Raissi 2019)
ML jet tagging (CMS 2014)
SINDy (Brunton 2016)
Explore the machine-learning-physics subtree on the interactive graph →