VicenteAlex/Spiking_ResNet

Implementation of the paper Keys to Accurate Feature Extraction Using Residual Spiking Neural Networks

23
/ 100
Experimental

This project offers an implementation of Spiking Residual Neural Networks (S-ResNets) for image classification tasks, specifically designed for neuromorphic computing. It takes image datasets like CIFAR-10, CIFAR-100, or DVS-CIFAR10 as input and produces a trained S-ResNet model capable of accurately classifying images. This is primarily for AI/ML researchers and engineers working on energy-efficient neural networks or biologically inspired AI.

No commits in the last 6 months.

Use this if you are an AI researcher or neuromorphic engineer looking to implement and experiment with spiking neural networks for image classification tasks, especially if energy efficiency is a key consideration.

Not ideal if you are looking for a general-purpose, off-the-shelf image classification solution using standard deep learning architectures or if you are not familiar with SNNs and neuromorphic concepts.

neuromorphic-computing spiking-neural-networks image-classification energy-efficient-AI bio-inspired-AI
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

35

Forks

3

Language

Python

License

Last pushed

Dec 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VicenteAlex/Spiking_ResNet"

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