Part 2 of a series of notebooks for teaching ML to early college students in an 8 week summer lab session. Covers Pandas.
Part 1 of a series of notebooks for teaching ML to early college students in an 8 week summer lab session.
A course taught at Cornell Tech where students build up the infrastructure behind vector autodifferentiation.
Literate blog on typed NN layers rotation with a Dex implementation.
A visual description of the adaptive sparse attention technique.
A visual description of banded sparse matrices, a really useful and underused form of sparsity.
Sat 05 January 2019 in Rants
Polemic about how tensors should be named in ML programming languages
Sat 05 January 2019 in Rants
Part 2 of a Polemic about how tensors should be named in ML programming languages.
In this post I present an "annotated" version of the paper in the form of a line-by-line implementation. I have reordered and deleted some sections from the original paper and added comments throughout.
