Effects of Introducing Synaptic Scaling on Spiking Neural Network Learning

2025-12-02

2025 10th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)

AI Summary

This work addresses the limited performance of spiking neural networks (SNNs) in unsupervised learning by integrating spike-timing-dependent plasticity (STDP) with L2-norm synaptic scaling within a winner-take-all (WTA) architecture. The study presents the first comprehensive evaluation of L2-norm synaptic scaling in SNN-based unsupervised learning, systematically investigating the effects of neuron count, STDP time constants, and synaptic weight normalization strategies. Experimental results demonstrate that the proposed approach significantly enhances classification accuracy under single-epoch training, achieving 88.84% on MNIST and 68.01% on Fashion-MNIST. These findings validate the efficacy and superiority of L2-norm synaptic scaling in improving unsupervised learning capabilities of SNNs.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Unsupervised & Self-Supervised Learning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Social networks and social learning
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Spiking neural networks (SNNs) employing unsupervised learning methods inspired by neural plasticity are expected to be a new framework for artificial intelligence. In this study, we investigated the effect of multiple types of neural plasticity, such as spike-time-dependent plasticity (STDP) and synaptic scaling, on the learning in a winner-take-all (WTA) network composed of spiking neurons. We implemented a WTA network with multiple types of neural plasticity using Python. The MNIST and the Fashion-MNIST datasets were used for training and testing. We varied the number of neurons, the time constant of STDP, and the normalization method used in synaptic scaling to compare classification accuracy. The results demonstrated that synaptic scaling based on the $\mathbf{L 2}$ norm was the most effective in improving classification performance. By implementing L2-normbased synaptic scaling and setting the number of neurons in both excitatory and inhibitory layers to 400, the network achieved classification accuracies of 88.84% on the MNIST dataset and 68.01% on the Fashion-MNIST dataset after one epoch of training.

Problem

• spiking neural networks
• synaptic scaling
• unsupervised learning
• neural plasticity
• classification accuracy

Innovation

• synaptic scaling
• spiking neural networks
• STDP
• L2 normalization
• unsupervised learning