james-simon/eigenlearning
codebase for "A Theory of the Inductive Bias and Generalization of Kernel Regression and Wide Neural Networks"
This project helps machine learning researchers and academics understand the fundamental principles governing how kernel regression and wide neural networks learn. It provides tools to generate synthetic and image datasets, and then test how these models perform, allowing you to replicate and explore the experimental results presented in the associated research paper. The typical user is someone conducting or studying advanced machine learning theory.
No commits in the last 6 months.
Use this if you are a machine learning theorist or researcher wanting to explore the inductive bias and generalization properties of kernel regression and wide neural networks.
Not ideal if you are looking for a practical tool to build or deploy machine learning models for real-world applications.
Stars
49
Forks
8
Language
Jupyter Notebook
License
—
Category
Last pushed
May 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/james-simon/eigenlearning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dnouri/nolearn
Combines the ease of use of scikit-learn with the power of Theano/Lasagne
PacktPublishing/Hands-On-Python-Deep-Learning-for-Web
Hands-On Python Deep Learning for Web by Anubhav Singh and Sayak Paul
mbadry1/Top-Deep-Learning
Top 200 deep learning Github repositories sorted by the number of stars.
CAIIVS/chuchichaestli
Where you find all the state-of-the-art cooking utensils (salt, pepper, gradient descent... the usual).
mbadry1/Trending-Deep-Learning
Top 100 trending deep learning repositories sorted by the number of stars gained on a specific day.