This simple mechanical system was one of my first coding projects when learning about physics simulations. It's basically a frictionless, gravity-free rigid pendulum that gets periodic kicks of fixed strength and direction. The phase space shows interesting patterns that are observed in multiple applications of chaos theory.
Would love to hear your thoughts and feedback, hope you like it!
PS I'm honestly blown away by how smooth is making webapps these days thanks to LLMs helping with all the web stack.
That actual content of that work was good but very misleading with an excess of backpropaganda and a poor literature review. The training procedure makes sense as continuous time backprop but it is mostly a special case of adjoint sensitivity analysis. The use of a NN as defining an ODE system seems fair to be named Neural ODE, imho its a good name, although again it was not completely novel as the writing style through the paper makes it look.
This kind of comment just enforces the defensive perception towards the community. He clearly stated that it was just his opinion. Why not just point out that "common tasks" always refers to each own's bubble?
I am a big fan of https://github.com/Evizero/UnicodePlots.jl . It is unexpected how useful these tools can be to track the evolution of numerical experiments/developments right on the terminal.
Would love to hear your thoughts and feedback, hope you like it!
PS I'm honestly blown away by how smooth is making webapps these days thanks to LLMs helping with all the web stack.