> be me
> dukenukem.jpg
> tired of playing ITCrowd.exe
> drool while looking at HMC.jpeg
> install numpyro
> assume homogeneous coupling
> random symmetry breaking
> try to recover broke symmetry
> time stepping sucks but required for HMC
> only care about covariance ("FC")
> take only one (big) step in time
> do that a lot (GPU FTW!)
> predict covariance
> oops
> how to pick initial conditions?
> or just iterate over onehot per roi?
> or use GPUs to learn good parametrizations of manifolds
> representations.... yum
> tired
> too_much_ikea_hot_wine.sh
> :wq<cr>
Last active
November 12, 2019 20:13
-
-
Save maedoc/a7dec3c3357c707543782a0f2842ce13 to your computer and use it in GitHub Desktop.
anon estimates manifolds
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment