Convolutional Spiking Neural Network for Image Classification

2025/05/13 by Kiselev, Mikhail, Lavrentyev, Andrey
#FOS: Computer and information sciences #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.2505.08514

Abstract

We consider an implementation of convolutional architecture in a spiking neural network (SNN) used to classify images. As in the traditional neural network, the convolutional layers form informational "features" used as predictors in the SNN-based classifier with CoLaNET architecture. Since weight sharing contradicts the synaptic plasticity locality principle, the convolutional weights are fixed in our approach. We describe a methodology for their determination from a representative set of images from the same domain as the classified ones. We illustrate and test our approach on a classification task from the NEOVISION2 benchmark.

Citations

• CoLaNET -- A Spiking Neural Network with Columnar Layered Architecture for Classification
• Spiking Convolutional Neural Networks for Text Classification
• Deep Spiking Convolutional Neural Network for Single Object Localization\n Based On Deep Continuous Local Learning
• Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook
• Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction
• SLAYER: Spike Layer Error Reassignment in Time

Related

• Classifying Images with CoLaNET Spiking Neural Network -- the MNIST Example
• A Digital Machine Learning Algorithm Simulating Spiking Neural Network CoLaNET
• STDP Learning of Image Patches with Convolutional Spiking Neural Networks
• Combining Spiking Neural Network and Artificial Neural Network for Enhanced Image Classification
• Deep Convolutional Spiking Neural Networks for Image Classification