EricZhang1412/Spatial-temporal-ERF

Official repo for NeurIPS 2025 poster: Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks

22
/ 100
Experimental

This project helps researchers in neuromorphic computing understand how Spiking Neural Networks (SNNs) process information over space and time. It takes trained SNN models and calculates their 'effective receptive fields,' which reveal what parts of the input an SNN layer truly focuses on. The output helps machine learning researchers and neuroscientists analyze and interpret SNN behavior, especially for visual tasks.

Use this if you are a researcher or engineer working with Spiking Neural Networks and need to analyze their internal mechanisms for visual processing, such as in detection or segmentation.

Not ideal if you are looking for a tool to build or train SNNs from scratch, or if your focus is on traditional deep learning models.

neuromorphic-computing spiking-neural-networks model-interpretability computer-vision neural-network-analysis
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

12

Forks

Language

Python

License

Last pushed

Jan 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EricZhang1412/Spatial-temporal-ERF"

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