HSG-AIML/SANE

Code Repository for the ICML 2024 paper: "Towards Scalable and Versatile Weight Space Learning".

31
/ 100
Emerging

This project helps machine learning researchers understand and work with large neural networks more effectively. It takes existing neural network models (like ResNet-18 trained on CIFAR-100) as input and provides a compact representation, or 'embedding,' for them. This allows you to predict model properties like accuracy or generalization gap, and even generate new, high-performing neural networks with less effort. This is ideal for machine learning engineers and researchers studying model behavior or exploring new architectures.

No commits in the last 6 months.

Use this if you need to analyze the internal properties of numerous large neural networks or efficiently generate new, well-performing model architectures.

Not ideal if you are looking for a tool to train neural networks from scratch or optimize hyper-parameters for a single specific model.

neural-network-analysis model-generation deep-learning-research model-understanding scalable-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

30

Forks

6

Language

Python

License

Last pushed

Sep 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HSG-AIML/SANE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.