Learning in Spiking Neural Networks with a Calcium-based Hebbian Rule for Spike-timing-dependent Plasticity

2025-04-09

AI Summary

To address the dual challenges of energy efficiency and adaptive learning in edge computing, this paper proposes a calcium-ion dynamics–driven local plasticity rule that unifies spike-timing-dependent plasticity (STDP) and rate-dependent plasticity into a biologically grounded synergistic mechanism. Unlike conventional approaches, the rule requires no explicit regulation of mean firing rates or manual tuning of learning hyperparameters, enabling energy-efficient, self-adaptive training of spiking neural networks (SNNs). We provide the first theoretical analysis and experimental validation demonstrating the complementary roles of temporal and rate-based information in synaptic plasticity. Evaluated on MNIST, the method achieves high recognition accuracy while successfully reproducing canonical neuroscientific phenomena—such as input-selective potentiation and homeostatic scaling—thereby bridging biological plausibility with computational efficacy. The framework is particularly suited for resource-constrained edge devices, offering a principled, low-power pathway toward adaptive neuromorphic intelligence.

Technology Category

Cognitive Modeling & Cognitive Systems: Neural Spike CodingMachine Learning: Learning on the Edge & Model CompressionSearch and Optimization: Learning to Search

Application Category

Economics, Online Markets and Human Computation: Social networks and social learningGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsUser Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Understanding how biological neural networks are shaped via local plasticity mechanisms can lead to energy-efficient and self-adaptive information processing systems, which promises to mitigate some of the current roadblocks in edge computing systems. While biology makes use of spikes to seamless use both spike timing and mean firing rate to modulate synaptic strength, most models focus on one of the two. In this work, we present a Hebbian local learning rule that models synaptic modification as a function of calcium traces tracking neuronal activity. We show how the rule reproduces results from spike time and spike rate protocols from neuroscientific studies. Moreover, we use the model to train spiking neural networks on MNIST digit recognition to show and explain what sort of mechanisms are needed to learn real-world patterns. We show how our model is sensitive to correlated spiking activity and how this enables it to modulate the learning rate of the network without altering the mean firing rate of the neurons nor the hyparameters of the learning rule. To the best of our knowledge, this is the first work that showcases how spike timing and rate can be complementary in their role of shaping the connectivity of spiking neural networks.

Problem

• Modeling synaptic plasticity using calcium traces in spiking neural networks
• Combining spike timing and rate for adaptive learning in neural networks
• Training spiking networks on real-world tasks like MNIST recognition

Innovation

• Calcium-based Hebbian rule for synaptic plasticity
• Combines spike timing and rate modulation
• Self-adaptive learning without altering firing rates