News for hackers. Stuff that matters.

A comment on Regularization is all you need: simple neural nets can excel on tabular data. Parent comment

Re:Regularization is all you need: simple neural nets can ex... by whatshisface on Tuesday June 22, 2021 @07:05PM (#27598461)
The table's the point cloud. I guess if you want to be really pedantic about grammar then I should point out that a set of one item is still a set. :-)
[ Parent | on HN ]
Re:Regularization is all you need: simple neural nets can ex... by asdf3331 on Tuesday June 22, 2021 @07:33PM (#27598753)
True - I misread your post. Your first post was intriguing but the second was dismissive. Surely there's more to be said than data sets are point clouds? Images are points in R^N too, right?
[ Parent | on HN ]
Re:Regularization is all you need: simple neural nets can ex... by whatshisface on Tuesday June 22, 2021 @08:12PM (#27599092)
If your unit of recognition was a set of images, and not an image alone, then you would have permutation symmetry and want to use point cloud techniques to design your first layer. So yes images are points in R^N.
[ Parent | on HN ]
Re:Regularization is all you need: simple neural nets can ex... by elcomet on Wednesday June 23, 2021 @02:26AM (#27601416)
Oh thanks, this was not clear from your other posts: the whole table is used as a data point, not the line. Much clearer now, why you would compare this to point clouds
[ Parent | on HN ]