# Axonal Delay As a Short-Term Memory for Feed Forward Deep Spiking Neural Networks

arXiv: https://arxiv.org/abs/2205.02115 · HTML: https://mlsanity.com/paper/2205.02115/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 8 of 8)

- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [S4NN: temporal backpropagation for spiking neural networks with one spike per neuron](https://mlsanity.com/paper/1910.09495/) (2019)
- [Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks](https://mlsanity.com/paper/1908.06378/) (2019)
- [Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain](https://mlsanity.com/paper/1807.01013/) (2018)
- [An efficient and perceptually motivated auditory neural encoding and decoding algorithm for spiking neural networks](https://mlsanity.com/paper/1909.01302/) (2019)

## Built on by (most cited first, 11 of 11)

- [Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings](https://mlsanity.com/paper/2306.17670/) (2023)
- [Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection](https://mlsanity.com/paper/2306.12010/) (2023)
- [Co-learning synaptic delays, weights and adaptation in spiking neural networks](https://mlsanity.com/paper/2311.16112/) (2023)
- [Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate](https://mlsanity.com/paper/2310.14982/) (2023)
- [The Role of Temporal Hierarchy in Spiking Neural Networks](https://mlsanity.com/paper/2407.18838/) (2024)
- [Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks](https://mlsanity.com/paper/2507.16043/) (2025)
- [Exploiting heterogeneous delays for efficient computation in low-bit neural networks](https://mlsanity.com/paper/2510.27434/) (2025)
- [Three factor delay learning rules for spiking neural networks](https://mlsanity.com/paper/2601.00668/) (2026)
- [Training Stronger Spiking Neural Networks with Biomimetic Adaptive Internal Association Neurons](https://mlsanity.com/paper/2207.11670/) (2022)
- [Hardware-aware training of models with synaptic delays for digital event-driven neuromorphic processors](https://mlsanity.com/paper/2404.10597/) (2024)
- [Prospective Messaging: Learning in Networks with Communication Delays](https://mlsanity.com/paper/2407.05494/) (2024)

## Abstract (arXiv)

The information of spiking neural networks (SNNs) are propagated between the adjacent biological neuron by spikes, which provides a computing paradigm with the promise of simulating the human brain. Recent studies have found that the time delay of neurons plays an important role in the learning process. Therefore, configuring the precise timing of the spike is a promising direction for understanding and improving the transmission process of temporal information in SNNs. However, most of the existing learning methods for spiking neurons are focusing on the adjustment of synaptic weight, while very few research has been working on axonal delay. In this paper, we verify the effectiveness of integrating time delay into supervised learning and propose a module that modulates the axonal delay through short-term memory. To this end, a rectified axonal delay (RAD) module is integrated with the spiking model to align the spike timing and thus improve the characterization learning ability of temporal features. Experiments on three neuromorphic benchmark datasets : NMNIST, DVS Gesture and N-TIDIGITS18 show that the proposed method achieves the state-of-the-art performance while using the fewest parameters.