#OTD in 1915, Leo Frank z"l was lynched by an antisemitic mob in Georgia, 2 yrs after he was unjustly convicted of murder in a trial marred by antisemitism. The revival of @paradebway reintroduced the public to this tragedy. Thank you to the cast & crew for sharing Frank's story.
Introducing NFNets, a family of image classification models that are:
*SOTA on ImageNet (86.5% top-1 w/o extra data)
*Up to 8.7x faster to train than EfficientNets to a given accuracy
*Normalizer-free (no BatchNorm!)
Paper: https://t.co/xvYDkgDCY0
Code: https://t.co/SmKU0gNCy7
Retweeting this one more time because it is so excellent, describes nicely how the mRNA vaccines are a direct hacking of Life's assembly code for the Spike protein + all of its headers, metadata, + tweaking it to be more stable and likely to evade the immune system defenses 👌👌
Actually it can be shown that convolution and transformer/attention are (almost) equivalent for graphs.
Architectures like Transformers and ConvNets are slowly but happily converging.
Today’s #UltimatePlay Card Spotlight: @AorusOfficial
Key Features:
⚪ WINDFORCE 3X Cooling System
⚪ RGB Fusion 2.0 – sync w/other AORUS devices
⚪ Protection metal back plate
Want your chance to win this card?
1. RT this post
2. Reply with #UltimatePlay
If Congress doesn’t bring fairness to Big Tech, which they should have done years ago, I will do it myself with Executive Orders. In Washington, it has been ALL TALK and NO ACTION for years, and the people of our Country are sick and tired of it!
This lecture by @MihaelaCRosca & Jeff Donahue looks at the theory behind GANs, the difficulties involved in optimising them & theoretical and empirical improvements to the basic framework.
https://t.co/UG3BJSjzld #AtHomeWithAI