Khochawongwat/GRAMKAN
KAN meets Gram Polynomials
This project offers a new way to build machine learning models for tasks like image recognition and text classification. It takes discretized data, such as pixel values from an image or tokenized text, and processes it through a unique neural network architecture that leverages Gram polynomial transformations. The output is a trained model capable of classifying or recognizing patterns in this data, designed for machine learning researchers and practitioners experimenting with novel model architectures.
No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner looking for an alternative neural network architecture specifically designed to handle discretized datasets like images or text more efficiently.
Not ideal if you are working with continuously defined data or prefer traditional, widely adopted neural network models for your applications.
Stars
19
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Khochawongwat/GRAMKAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIAGameWorks/kaolin
A PyTorch Library for Accelerating 3D Deep Learning Research
Jim137/qkan
PyTorch implementation of QKAN "Quantum-inspired Kolmogorov-Arnold Network"...
AntonioTepsich/Convolutional-KANs
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN)...
lgy112112/ikan
ikan: many kan variants for every body
Indoxer/LKAN
Variations of Kolmogorov-Arnold Networks