qkan and KAN-PyTorch

These are competitors offering alternative PyTorch implementations of Kolmogorov-Arnold Networks, with A extending the concept to quantum-inspired variants while B provides a foundational KAN implementation, so users would typically choose one based on whether they need quantum inspiration or classical KAN architecture.

qkan
58
Established
KAN-PyTorch
33
Emerging
Maintenance 10/25
Adoption 7/25
Maturity 24/25
Community 17/25
Maintenance 0/25
Adoption 7/25
Maturity 16/25
Community 10/25
Stars: 20
Forks: 8
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 25
Forks: 3
Downloads:
Commits (30d): 0
Language: Python
License: GPL-3.0
No risk flags
Stale 6m No Package No Dependents

About qkan

Jim137/qkan

PyTorch implementation of QKAN "Quantum-inspired Kolmogorov-Arnold Network" https://arxiv.org/abs/2509.14026

This tool helps researchers and machine learning practitioners build and train "Quantum-inspired Kolmogorov-Arnold Networks" (QKANs). It takes raw data and model configuration to produce trained models that can fit functions, classify data, or generate new data. This is ideal for those exploring advanced neural network architectures, especially those interested in quantum computing's influence on AI.

quantum-machine-learning neural-network-research function-approximation data-classification generative-modeling

About KAN-PyTorch

Simon-Bertrand/KAN-PyTorch

Kolmogorov–Arnold Networks (KAN) in PyTorch

This is a specialized tool for machine learning researchers and practitioners who are experimenting with novel neural network architectures. It allows you to build models using Kolmogorov-Arnold Networks (KANs), which are an alternative to traditional Multi-Layer Perceptrons (MLPs). You input your dataset and get a KAN-based model that can be trained for tasks like classification.

deep-learning-research neural-network-design machine-learning-experimentation model-architecture scientific-machine-learning

Scores updated daily from GitHub, PyPI, and npm data. How scores work