Grokking: Generalization beyond Overfitting on small algorithmic datasets (Paper Explained)

(29:47)

Ep 36. Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

(7:43)

The elusive generalization: classical bounds to double descent to grokking

(1:19:56)

New Discovery: LLMs have a Performance Phase

(29:51)

Why \

(13:36)

Double Descent explained by Yann LeCun

(4:19)

Generalization and Overfitting

(6:57)

LLM - Reasoning SOLVED (new research)

(47:51)

Grokking at the Edge of Numerical Stability

(17:10)

[LIVE] Rasa Reading Group: Grokking: Generalisation beyond overfitting on small algorithmic datasets

(51:37)

Accelerated Training by Amplifying Slow Gradients

(26:29)

Training and generalization dynamics in simple deep networks

(33:8)

Generalization and Overfitting

(44)

Machine Learning Crash Course: Generalization

(1:59)

why grokking discovery was crazy #machinelearning #grok https://arxiv.org/pdf/2201.02177.pdf

(57)

Generalization

(1:15)

Understanding Deep Neural Networks: From Generalization to Interpretability - Gitta Kutyniok

(1:2:4)

Explaining Grokking Through Circuit Efficiency

(39:19)

An Observation on Generalization

(57:21)

Lecture 1: Understanding Generalization Requires Rethinking Deep Learning (English)

(1:15:42)