Skip to content

llfuller/NeuralNetworkNewton

Repository files navigation

NeuralNetworkNewton

Learning kinematic behavior and elastic collisions by watching point particles collide. Independent project for neurodynamics course Phys279 at UCSD.

Result Summary: Doesn't work very well.

How to get started: Run SimulateCollisions.py to generate collisions and all state variables + time data for two particles. Run SimulateMisses.py to generate mixed collision/non-collision data.

Extra notes: CheckConservation.py checks that energy and momentum are conserved by the collisions. CheckPosition.py graphs position of particles as they collide.

About

Learning Newton's laws of motion by watching point particles collide.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages