Solve PDEs and run differentiable physics simulations with JAX.
npx skills add https://github.com/tondevrel/scientific-agent-skills --skill jax-pde
Please help me install this Agent Skill. Skill: jax-pde Source: https://github.com/tondevrel/scientific-agent-skills/tree/main/skills/jax-pde Command: npx skills add https://github.com/tondevrel/scientific-agent-skills --skill jax-pde
This Skill enables the solution of complex Partial Differential Equations (PDEs) and the development of differentiable physics models using the JAX library, bridging traditional numerical methods with modern machine learning techniques.
Use the jax-pde skill to implement a PINN for solving the Burgers' equation.
High-intent search queries and answers about installing and using this skill.
To solve partial differential equations with JAX, you can use physics-informed neural networks that enforce physical laws as constraints, or apply finite difference methods on grids for forward and inverse scientific computing problems.
Differentiable physics simulation uses JAX automatic differentiation to compute gradients directly through PDE solvers. This enables efficient sensitivity analysis and gradient-based optimization for inverse problems in scientific computing.
Yes, you can apply and differentiate traditional finite difference methods for solving PDEs on grids. JAX enables gradient computation through these numerical solvers, bridging conventional methods with differentiable physics simulations.
You optimize material properties by defining an objective function that compares simulation results with experimental data. JAX automatically computes the gradients of this objective with respect to physical properties like viscosity, enabling efficient inverse problem solving.
Yes, you need JAX installed because the skill requires JAX for automatic differentiation and numerical computation on hardware accelerators to execute and differentiate finite difference method solvers.
GeneralReasoningLoad, map, reduce, differentiate, scan, and JIT-compile arrays with JAX.
sangrokjungCalculate financial ratios and run DCF valuation models with Python scripts.
xjtulycTrain physics-informed neural networks with PyTorch autograd for PDEs and ODEs.
synapticore-ioSolve PDE-based modeling problems with physics-informed neural networks in PyTorch.
