News for hackers. Stuff that matters.

A comment on The Decade of Deep Learning. Parent comment

Re:The Decade of Deep Learning by pmoriarty on Saturday April 15, 2023 @09:26AM (#35580438)
Shouldn't this argument be easy to settle with a simple citation search?

Step 1 - Rank papers by number of citations

Step 2 - Which of the most cited papers is the earliest?

[ Parent | on HN ]
Re:The Decade of Deep Learning by kgwgk on Saturday April 15, 2023 @10:04AM (#35580730)
One paper will be the most cited. One paper will be the earliest.

Unless they are the same there is not _one_ answer, what you get is an efficient set (the earliest paper with at least X citations / the most cited paper as of D).

And of course there is the problem of making the list of relevant papers in the first place.

[ Parent | on HN ]