aitor-martinez-seras/OoD_on_SNNs
Explainable Out-of-Distribution Detection Approach for Spiking Neural Networks (Code for "A Novel Out-of-Distribution Detection Approach for Spiking Neural Networks: Design, Fusion, Performance Evaluation and Explainability")
This project helps machine learning practitioners evaluate how well their Spiking Neural Networks (SNNs) can detect data that is 'out-of-distribution' (OoD). It takes trained SNN models and various image datasets (both in-distribution and OoD) as input, and provides performance metrics and visual explanations (attribution maps) showing why a sample was flagged as OoD. The primary users are researchers and engineers working with SNNs who need to ensure their models are reliable when encountering unexpected data.
No commits in the last 6 months.
Use this if you are developing or deploying Spiking Neural Networks and need to rigorously test their ability to identify data that significantly differs from their training examples.
Not ideal if you are working with traditional Artificial Neural Networks (ANNs) or need a general-purpose OoD detection library that isn't specifically tailored for SNNs.
Stars
8
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aitor-martinez-seras/OoD_on_SNNs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yzhao062/pyod
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
unit8co/darts
A python library for user-friendly forecasting and anomaly detection on time series.
elki-project/elki
ELKI Data Mining Toolkit
raphaelvallat/antropy
AntroPy: entropy and complexity of (EEG) time-series in Python
Minqi824/ADBench
Official Implement of "ADBench: Anomaly Detection Benchmark", NeurIPS 2022.