Thanks to @Cults3D for a great platform for showing and distributing #mathart! (The big star isn't mine, but I had a hand in it!) https://t.co/v5hqnV4ddl
Neural ODEs are slow. We speed them up by regularizing their higher derivatives, learning ODEs that are easy to solve:
https://t.co/MdSPa9f8Mt
with @jacobjinkelly@jessebett@SingularMattrix
Penrose tiling are aperiodic tilings obtained using typically 2 isosceles triangles with 2 types of edge labelings (so 4 types of triangles). A way to generate tilings is by applying iterative edge splitting using the golden ratio. https://t.co/mZhDqpOC6v https://t.co/Pl7xlleHhT
We just open-sourced differentiable SDE solvers in PyTorch:
https://t.co/v1f08mjgCq
Now you can put stochastic differential equations in your deep learning models, and neural nets in your SDEs! Credit to @lxuechen.
Leapfrog/Verlet are symplectic integrators which approximately conserve hamiltonian, preserve periodic behaviors and are exactly reversible. https://t.co/MVKkciHpOL https://t.co/3cJCKZ3WE3