HSG-AIML/NeurIPS_2022-Generative_Hyper_Representations

Code Repository for the NeurIPS 2022 paper: "Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights".

27
/ 100
Experimental

This project helps machine learning researchers explore and generate new neural network models. It takes existing collections of pre-trained models (model zoos) as input and can generate novel model weights that are diverse, performant, and can be used for various downstream tasks. Machine learning researchers and practitioners interested in advanced model creation and analysis would find this useful.

No commits in the last 6 months.

Use this if you are a machine learning researcher looking to generate new neural network architectures or weights for tasks like neural architecture search, model initialization, or ensemble creation.

Not ideal if you are looking for a straightforward tool to train a single model for a specific task without exploring advanced generative model techniques.

Machine Learning Research Neural Network Design Generative Models Model Zoos AI Innovation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Python

License

MIT

Last pushed

Jul 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HSG-AIML/NeurIPS_2022-Generative_Hyper_Representations"

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