If you can find a random initialization that by coincidence happens to get >94% of 60,000 10-class classification decisions correct then yes, that counts.
MACHINE LEARNING
-
Random Seeds and Model Evaluation: The Coincidence Problem
By
–
If you can find a random seed that by coincidence happens to get >94% of 60,000 10-class classification decisions correct then yes, that counts.
-
Instruction tuning merges human will into AI controlled by awkward kid
By
–
Instruction tuning / RLHF is technically a Human Instrumentality Project, merging the preferences of countless humans to form an oversized, living amalgam of our will. We then hand control of it to a random, socially awkward kid and hope for the best.
-
Metis AI Platform Accelerates Computer Vision at Edge
By
–
We’re extremely proud to announce our Metis AI Platform to accelerate computer vision at the edge. Explore the Metis AI Platform for yourself on our new website, https://
axelera.ai #ArtificialIntelligence #MachineLearning #computervision -
AI and Autonomous Vehicles: Focus on LabCom AI4MOBLAB
By
–
AI and Autonomous Vehicles: Focus on LabCom AI4MOBLAB https://actuia.com/actualite/ia-et-vehicules-autonomes-focus-sur-le-labcom-ai4moblab/
… #AI #artificialintelligence #mobility -
Plain ResNet with GeneralRelu and 1Cycle Training
By
–
It's the plainest possible resnet with GeneralRelu, adamw, and 1cycle training.
-
Challenge to Beat Best Results in 20 Epochs
By
–
I'll take a look! See what you can get in 20 epochs – would love to see my best get beaten 😀
-
New 5-Epoch Leaderboard: Achieving 92.7% Performance
By
–
Opening up a new leaderboard – best in 5 epochs. I just got 92.7% 🙂
-
ResNet Model Achieves 93.2% Accuracy with Custom Augmentation
By
–
So far my best is 93.2% using a custom resnet and flip/crop random augmentation. Can anyone beat that?