Windere/ASGL-SNN

Offical implementation of "Adaptive Smoothing Gradient Learning for Spiking Neural Networks", ICML 2023

19
/ 100
Experimental

This project offers a new way to train Spiking Neural Networks (SNNs) for tasks like image recognition, using a method called Adaptive Smoothing Gradient Learning (ASGL). It takes raw image datasets (like CIFAR-10, CIFAR-100, DVS-CIFAR10) and processes them to produce more accurate and robust SNN models. This is useful for AI researchers and engineers who develop energy-efficient neural networks for various applications.

No commits in the last 6 months.

Use this if you are a researcher or engineer working with Spiking Neural Networks and want to improve their training accuracy, especially when dealing with noisy or complex data.

Not ideal if you are looking for a general-purpose deep learning library or if your primary interest is in traditional Artificial Neural Networks rather than SNNs.

Spiking-Neural-Networks Deep-Learning-Research Image-Recognition Neuromorphic-Computing Machine-Learning-Optimization
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Python

License

Last pushed

Aug 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Windere/ASGL-SNN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.