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".
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.
Stars
22
Forks
3
Language
Python
License
—
Category
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.
Higher-rated alternatives
zeiss-microscopy/OAD
Collection of tools and scripts useful to automate microscopy workflows in ZEN Blue using Python...
median-research-group/LibMTL
A PyTorch Library for Multi-Task Learning
qdrant/quaterion
Blazing fast framework for fine-tuning similarity learning models
lucidrains/PoPE-pytorch
Efficient implementation (and explorations) into polar coordinate positional embedding (PoPE) -...
MR-HosseinzadehTaher/BenchmarkTransferLearning
Official PyTorch Implementation and Pre-trained Models for Benchmarking Transfer Learning for...