Einsum Is All You Need – Einstein Summation in Deep Learning (2018)

Re:Einsum Is All You Need – Einstein Summation in Deep Learn... by mhh__ on Saturday February 02, 2019 @10:26PM (#19067641)

Absolutely yes.

Doing tensor magic without einstein notation will make you shoot yourself, and even you don't someone else will if publish it.

The only real problem I have with it personally is the abstraction of upper and lower indices, which I constantly forget the conventions as to which is which.

[ Parent | on HN ]

Re:Einsum Is All You Need – Einstein Summation in Deep Learn... by krastanov on Sunday February 03, 2019 @02:12AM (#19068254)

This is interesting... I love the notation, but mainly because how upper and lower indices make it easy to distinguish vectors and forms (not that it matters in ML where everything is "euclidean").

[ Parent | on HN ]

Re:Einsum Is All You Need – Einstein Summation in Deep Learn... by joppy on Sunday February 03, 2019 @04:01AM (#19068518)

Upper and lower indices are great, but are still unrelated to the convention of dropping the big sigma at the front.

[ Parent | on HN ]

Re:Einsum Is All You Need – Einstein Summation in Deep Learn... by antidesitter on Sunday February 03, 2019 @11:18AM (#19070402)

> not that it matters in ML where everything is "euclidean"

Non-euclidean spaces are actually quite common in ML, but many people don’t realize the spaces they’re working in are non-euclidean!

[ Parent | on HN ]

Re:Einsum Is All You Need – Einstein Summation in Deep Learn... by improbable22 on Sunday February 03, 2019 @02:02PM (#19071456)

Would be curious to hear what you have in mind here -- could you expand?

[ Parent | on HN ]

Re:Einsum Is All You Need – Einstein Summation in Deep Learn... by g82918 on Tuesday February 05, 2019 @10:09PM (#19092367)

Co -> low, primes below.

[ Parent | on HN ]