danielmamay/grokking
Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.
This project helps machine learning researchers explore the 'grokking' phenomenon, where models generalize to unseen data long after overfitting on the training data. You can feed in small algorithmic datasets and observe how different model architectures and training parameters affect this delayed generalization. It's designed for researchers focused on understanding the fundamental learning dynamics of neural networks, particularly in areas like interpretability and generalization theory.
No commits in the last 6 months.
Use this if you are a machine learning researcher studying how neural networks achieve generalization, especially on small, synthetic datasets, and want to experiment with factors influencing the 'grokking' effect.
Not ideal if you are looking to apply machine learning to real-world, large-scale datasets or build production-ready applications, as this tool is for fundamental research into model behavior.
Stars
42
Forks
12
Language
Python
License
MIT
Category
Last pushed
Sep 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danielmamay/grokking"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/Paddle
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice...
fastai/fastai
The fastai deep learning library
openvinotoolkit/openvino_notebooks
📚 Jupyter notebook tutorials for OpenVINO™
PaddlePaddle/docs
Documentations for PaddlePaddle
msuzen/bristol
Parallel random matrix tools and complexity for deep learning