tweetindex

Keller Jordan @kellerjordan0 · 13 Apr 2023

2/ Background: for standard CIFAR-10 trainings there exist rare “lucky seeds/runs” attaining over +0.5% higher test-set accuracy than the average (10% fewer errors). ImageNet trainings are similar with +0.4%. These differences are considered significant in computer vision.
8 558Views
55Likes
0Reposts
2Replies
0Quotes
2Bookmarks

Is that a lot?

0.92×vs this author's median9 348 views is typical
0Percentile for this authorof 5 recent posts
5.88×vs 10K–100K median1 456 views is typical
44.30%Reachviews ÷ followers
0.67%Engagement rateof viewers reacted

Compare with the benchmark table →

Open on X →