A differentially private spiking neural network with temporal enhanced pooling

Source code of the paper entitled "Improving Fraud Detection with 1D-Convolutional Spiking Neural Networks through Bayesian Optimization", and presented at EPIA 2024, the 23rd International Conference on Artificial Intelligence.

🧠⚡ NeuroEvo Cleaners Spiking Neural Networks that evolve to master complex trash collection tasks

This repository trains a spiking neural network (SNN) classifier on the MNIST dataset using various spike encoding techniques. It explores different encoding schemes to convert images into spike trains and evaluates their impact on classification performance with the help of the SNNTorch module.

SNN Control System for Superconducting Transmon Qubits

Train Spiking Neural Networks for a Biomimetic Eye

Source code of the paper entitled "Exploring Neural Joint Activity in Spiking Neural Networks for Fraud Detection", and presented at CIARP 2024, the 27th Iberamerican Congress on Pattern Recognition.

SOS.net (v2): YOLOv3 x SNN computer vision for optimized drone search-and-rescue.

image segmentation using spiking neural network

Basic applications of SNN computer vision (snnTorch).

Spiking ResNet‑18 (snnTorch) for blood‑pressure prediction from PPG. Implements PA‑B residual connections and Densely Additive Connections (Li et al., Rethinking residual connection in training large-scale spiking neural networks). Includes preprocessing for the bp‑benchmark dataset (González et al.).

Spiking Neural Network Image Classification with SNN-Torch and Gradio. This project features a Spiking Neural Network (SNN) built using SNN-Torch for classifying images. SNNs are energy-efficient, biologically inspired models. The project aims to showcase abilities of Spiking Neural Networks to classify images and Gradio to create the model demo.

Code used to develop and test a Spiking Neural Network model to classify MNIST and Fashion-MNIST datasets

This repository explores Spiking Neural Networks (SNNs) and Continual Learning (CL) techniques for autonomous driving tasks, focusing on domain-incremental learning.

Recurrent spiking network models for predicting MNIST sequences