Sparse Axonal and Dendritic Delays Enable Competitive SNNs for Keyword Classification

2026-02-10

AI Summary

This work proposes a feedforward spiking neural network (SNN) architecture incorporating learnable axonal and dendritic delays, combined with leaky integrate-and-fire (LIF) neurons and a delay sparsification strategy, to address the high computational and memory overhead of SNNs in complex temporal tasks. The study presents the first systematic comparison between axonal and dendritic delay mechanisms, demonstrating that both achieve competitive performance even under extreme sparsity—retaining only 20% of active delays—significantly outperforming conventional synaptic delay approaches. The proposed model attains 95.58% accuracy on the Google Speech Commands dataset and 80.97% on the Spiking Speech Commands dataset, while substantially reducing buffer requirements and overall resource consumption.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Training transmission delays in spiking neural networks (SNNs) has been shown to substantially improve their performance on complex temporal tasks. In this work, we show that learning either axonal or dendritic delays enables deep feedforward SNNs composed of leaky integrate-and-fire (LIF) neurons to reach accuracy comparable to existing synaptic delay learning approaches, while significantly reducing memory and computational overhead. SNN models with either axonal or dendritic delays achieve up to $95.58\%$ on the Google Speech Command (GSC) and $80.97\%$ on the Spiking Speech Command (SSC) datasets, matching or exceeding prior methods based on synaptic delays or more complex neuron models. By adjusting the delay parameters, we obtain improved performance for synaptic delay learning baselines, strengthening the comparison. We find that axonal delays offer the most favorable trade-off, combining lower buffering requirements with slightly higher accuracy than dendritic delays. We further show that the performance of axonal and dendritic delay models is largely preserved under strong delay sparsity, with as few as $20\%$ of delays remaining active, further reducing buffering requirements. Overall, our results indicate that learnable axonal and dendritic delays provide a resource-efficient and effective mechanism for temporal representation in SNNs. Code will be made available publicly upon acceptance. Code is available at https://github.com/YounesBouhadjar/AxDenSynDelaySNN

Problem

• spiking neural networks
• temporal representation
• keyword classification
• transmission delays
• computational efficiency

Innovation

• axonal delays
• dendritic delays
• spiking neural networks
• delay sparsity
• temporal representation