Scientific Machine Learning

concepts · 6 notes linked

Related: Neural Operators · Jax · Weights And Biases · Physics Informed Neural Networks · Neural Tangent Kernel · Caltech · Brown University · Partial Differential Equations

Notes

• GitHub - PredictiveIntelligenceLab/jaxpi — JAX library implementing physics-informed neural networks with benchmarks
• Latest Neural Nets Solve World's Hardest Equations Faster Than Ever Before — Neural operators learn mappings between function spaces to solve PDE families
• New AI framework turns any laptop into a supercomputer — DIMON AI framework solves PDEs across geometries on commodity hardware
• Physics-based Deep Learning — Hands-on guide to deep learning methods for physical simulations
• Scientists use generative AI to answer complex questions in physics — MIT framework uses generative models to automatically map physics phase diagrams
• Surrogates for Physics-based and Data-driven Modelling of Parametric Systems: Review and New Perspectives — Unified review of physics-based, data-driven, and hybrid surrogate models for parametric systems