Combining Convolution and Delay Learning in Recurrent Spiking Neural Networks

Lúcio Folly Sanches Zebendo; Eleonora Cicciarella; Michele Rossi

cs.NEApr 17, 2026

Combining Convolution and Delay Learning in Recurrent Spiking Neural Networks

Authors: Lúcio Folly Sanches Zebendo, Eleonora Cicciarella, Michele Rossi

Organizations: University of Padova, Department of Information Engineering · Department of Mathematics “Tullio Levi Civita” at the University of Padova, Italy

Abstract

Spiking neural networks (SNNs) are rapidly gaining momentum as an alternative to conventional artificial neural networks in resource constrained edge systems. In this work, we continue a recent research line on recurrent SNNs where axonal delays are learned at runtime along with the other network parameters. The first proposed approach, dubbed DelRec, demonstrated the benefit of recurrent delay learning in SNNs. Here, we extend it by advocating the use of convolutional recurrent connections in conjunction with the DelRec delay learning mechanism. According to our tests on an audio classification task, this leads to a streamlined architecture with smaller memory footprint (around 99% savings in terms of number of recurrent parameters) and a much faster (52x) inference time, while retaining DelRec's accuracy. Our code is available at: https://github.com/luciozebendo/delrec_snn/tree/conv_delays

Explore similar work

Congestion-Aware Dynamic Axonal Delay for Spiking Neural Networks
May 2, 2026Dewei Bai, Hongxiang Peng, Yunyun Zeng +2Spiking Neural Networks Binary Spikes
Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation
May 1, 2026Bo Tang, Weiwei XieSpiking Neural Networks Recurrent Neural Networks
Hybrid ANN-SNN Pipeline with Local Plasticity
Jun 18, 2026Denis Larionov, Khairutin Shtanchaev, Mikhail Kiselev +2Spiking Neural Networks Binary Spikes

May 2, 2026 · cs.LGJ/K move · Enter open · S save

Congestion-Aware Dynamic Axonal Delay for Spiking Neural Networks

Dewei Bai, Hongxiang Peng, Yunyun Zeng, Ziyu Zhang+1

University of Electronic Science and Technology of China

Spiking Neural Networks (SNNs) are widely regarded as an energy-efficient paradigm for modeling and processing temporal and event-driven information. Incorporating delays in SNNs has been proven to be an effective mechanism for improving spike alignment in event-driven tasks. However, existing delay learning approaches predominantly assign static delays to individual synapses, resulting in a large number of delay parameters and limited adaptability to input-dependent activity dynamics. To this end, we propose a Congestion-Aware Dynamic Axonal Delay (CADAD) mechanism, which decomposes the delay into a channel-wise static base delay for temporal structuring and a global, activity-conditioned shift that dynamically regulates the state update rate under varying spike intensities. The delay parameters are learned using differentiable linear interpolation and discretized at inference time, preserving the benefits of dynamic delay modulation while incurring only minimal additional cost. Experiments on speech benchmarks, including the Spiking Heidelberg Dataset, Spiking Speech Commands, and Google Speech Commands, demonstrate that introducing congestion-aware delays into synaptic signal transmission effectively improves accuracy on temporal tasks, notably achieving 93.75% accuracy on SHD, 80.69% accuracy on SSC, and 95.58% on GSC-35, while reducing the parameter count by approximately 50% compared to state-of-the-art delay-based methods with the same architecture.

Spiking Neural Networks Binary Spikes Synaptic Plasticity Delay Sparse Expert Activation Neural Network

Open paper Ask about it PDF

Abstract

Explore similar work

Congestion-Aware Dynamic Axonal Delay for Spiking Neural Networks

Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation

Hybrid ANN-SNN Pipeline with Local Plasticity