Grokking: Generalization beyond Overfitting on small algorithmic datasets (Paper Explained) Published 2021-10-06 Download video MP4 360p Recommendations 24:07 AI can't cross this line and we don't know why. 20:18 Why Does Diffusion Work Better than Auto-Regression? 19:40 We FINALLY Understand Why Tardigrades Refuse to Die 17:16 How Physicists FINALLY Solved the Feynman Sprinkler Problem - Explained 46:32 Deep Ensembles: A Loss Landscape Perspective (Paper Explained) 13:36 Why "Grokking" AI Would Be A Key To AGI 11:40 Regularization in a Neural Network | Dealing with overfitting 26:29 Accelerated Training by Amplifying Slow Gradients 06:41 AI’s Dirty Little Secret 28:12 MLP-Mixer: An all-MLP Architecture for Vision (Machine Learning Research Paper Explained) 04:19 Double Descent explained by Yann LeCun 56:16 Flow Matching for Generative Modeling (Paper Explained) 58:37 Yann LeCun - Self-Supervised Learning: The Dark Matter of Intelligence (FAIR Blog Post Explained) 38:27 ICLR 2021 Keynote - "Geometric Deep Learning: The Erlangen Programme of ML" - M Bronstein 11:47 What the HECK is a Tensor?!? Similar videos 51:37 [LIVE] Rasa Reading Group: Grokking: Generalisation beyond overfitting on small algorithmic datasets 02:04 Tips for working with small datasets 00:23 How to Fix Machine Learning Models #shorts 48:23 Eric Michaud—Scaling, Grokking, Quantum Interpretability More results