Just to keep this open, here is a favourite statistical joke. The familiar practical definition of a median is that it is the middle ordered value when the number of values is odd and the mean of the two middle ordered values when it is even. But what do you call those two middle values? They are, naturally enough, comedians. (I believe this was thought up independently by Stephen Stigler and Roger Koenker.)
@NickCox, please post that on the main site. There we have better facilities for asking & answering questions (e.g. formatting options will work) and the information will be available for people with the same question. That isn't a chat item.
Hey, I felt like we were missing some questions on the newest neural stuff, so I went ahead and asked two questions. The one on the NeuralODE paper got an answer from David Duvenaud (or I hope it's him for real), how cool is that?
"Neural Ordinary Differential Equations", by Tian Qi Chen, Yulia Rubanova, Jesse Bettencourt and David Duvenaud, was awarded the best-paper award in NeurIPS in 2018
There, authors propose the NeuralODE, which is a method that fuses concepts of Differential Equations and Neural Networks. Borrowin...