MinaGhadimiAtigh/Hyperbolic-Busemann-Learning
Hyperbolic Busemann Learning with Ideal Prototypes, NeurIPS2021
This project helps machine learning practitioners or researchers working with classification tasks. It takes your dataset and learns 'ideal prototypes' for each category, which are then used to improve the accuracy of the main classification model. The output includes these learned prototypes and the results from the classification model.
No commits in the last 6 months.
Use this if you are exploring advanced techniques for classification problems and want to leverage hyperbolic geometry to potentially improve model performance, especially in cases with many classes or complex class relationships.
Not ideal if you are looking for a simple, out-of-the-box solution for standard classification without diving into the underlying mathematical concepts and model tuning.
Stars
25
Forks
4
Language
Python
License
—
Category
Last pushed
Dec 09, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MinaGhadimiAtigh/Hyperbolic-Busemann-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...