mlbio-epfl/hume
[NeurIPS 2023 Spotlight] The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning
This project helps machine learning researchers and practitioners understand how a human might categorize data without needing to manually label anything. You provide two sets of numerical representations (embeddings) for your dataset, and it outputs inferred human-like groupings or categories. It's designed for those working with large, unlabeled datasets who want to discover natural, interpretable structures.
No commits in the last 6 months.
Use this if you have a dataset with rich, pre-computed numerical features and want to automatically uncover potential human-interpretable categories or clusters without any manual labeling.
Not ideal if you need a specific, predefined set of labels or if you don't have existing high-quality numerical representations of your data.
Stars
19
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mlbio-epfl/hume"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification