HSG-AIML/NeurIPS_2021-Weight_Space_Learning

Code Repository for the NeurIPS 2021 paper: "Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction".

25
/ 100
Experimental

This project helps machine learning researchers and practitioners evaluate and understand their neural network models more efficiently. It takes populations of trained neural networks (model zoos) as input and generates 'neural representations' of their internal structures. These representations can then be used to predict various model characteristics, helping users decide which models are best suited for specific tasks without extensive retraining.

No commits in the last 6 months.

Use this if you need to analyze and predict the behavior or performance of many trained neural networks without running extensive, time-consuming experiments on each one.

Not ideal if you are working with individual models or don't have a large collection (zoo) of trained neural networks to analyze.

machine-learning-research model-evaluation neural-network-analysis model-selection deep-learning-operations
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

22

Forks

3

Language

Python

License

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_2021-Weight_Space_Learning"

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