NeuralPDE.jl icon indicating copy to clipboard operation
NeuralPDE.jl copied to clipboard

Add a more performant approximation for directional derivatives

Open xtalax opened this issue 1 year ago • 0 comments

Directional derivatives are currently calculated by first calculating all the variable derivs and then performing a weighted sum.

This could be more efficient, especially with many dimensions.

Actions to take:

  • [ ] Add a Nabla/Del operator to symbolics
  • [ ] Recognise directional derivs and dispatch a more performant apporximation

xtalax avatar Jul 17 '23 19:07 xtalax