# One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latency

arXiv: https://arxiv.org/abs/2110.05929 · HTML: https://mlsanity.com/paper/2110.05929/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 49 references that are in the map.
- First posted on arXiv 1 Oct 2021.

## Builds on (most cited first, 30 of 30)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [Going Deeper in Spiking Neural Networks: VGG and Residual Architectures](https://mlsanity.com/paper/1802.02627/) (2018)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [Long short-term memory and learning-to-learn in networks of spiking neurons](https://mlsanity.com/paper/1803.09574/) (2018)
- [RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2003.01811/) (2020)
- [Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation](https://mlsanity.com/paper/2005.01807/) (2020)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures](https://mlsanity.com/paper/1903.06379/) (2019)
- [Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks](https://mlsanity.com/paper/2002.10085/) (2020)
- [Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratch](https://mlsanity.com/paper/2010.01729/) (2020)
- [DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks](https://mlsanity.com/paper/2008.03658/) (2020)
- [Spiking Deep Networks with LIF Neurons](https://mlsanity.com/paper/1510.08829/) (2015)
- [Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students](https://mlsanity.com/paper/1805.05551/) (2018)
- [Gradient Descent for Spiking Neural Networks](https://mlsanity.com/paper/1706.04698/) (2017)
- [T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding](https://mlsanity.com/paper/2003.11741/) (2020)
- [Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagation](https://mlsanity.com/paper/1907.13223/) (2019)
- [Exploring the Connection Between Binary and Spiking Neural Networks](https://mlsanity.com/paper/2002.10064/) (2020)
- [Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks](https://mlsanity.com/paper/1809.03142/) (2018)
- [Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks](https://mlsanity.com/paper/2009.14456/) (2020)
- [A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks](https://mlsanity.com/paper/1907.01167/) (2019)

## Built on by (most cited first, 17 of 17)

- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Attention Spiking Neural Networks](https://mlsanity.com/paper/2209.13929/) (2022)
- [Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks](https://mlsanity.com/paper/2302.14311/) (2023)
- [Exploring Temporal Information Dynamics in Spiking Neural Networks](https://mlsanity.com/paper/2211.14406/) (2022)
- [TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agents](https://mlsanity.com/paper/2303.01826/) (2023)
- [Hoyer regularizer is all you need for ultra low-latency spiking neural networks](https://mlsanity.com/paper/2212.10170/) (2022)
- [SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents](https://mlsanity.com/paper/2404.09331/) (2024)
- [Direct Training via Backpropagation for Ultra-low Latency Spiking Neural Networks with Multi-threshold](https://mlsanity.com/paper/2112.07426/) (2021)
- [Spiking Neural Networks: The Future of Brain-Inspired Computing](https://mlsanity.com/paper/2510.27379/) (2025)
- [S3NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networks](https://mlsanity.com/paper/2201.10879/) (2022)
- [Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model](https://mlsanity.com/paper/2305.16340/) (2023)
- [Spike Accumulation Forwarding for Effective Training of Spiking Neural Networks](https://mlsanity.com/paper/2310.02772/) (2023)
- [Spiking Synaptic Penalty: Appropriate Penalty Term for Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2302.01500/) (2023)
- [HyperSNN: A new efficient and robust deep learning model for resource constrained control applications](https://mlsanity.com/paper/2308.08222/) (2023)
- [Energy-Efficient Visual Search by Eye Movement and Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2310.06578/) (2023)
- [Web Neural Network with Complete DiGraphs](https://mlsanity.com/paper/2401.04134/) (2024)
- [SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization](https://mlsanity.com/paper/2508.10913/) (2025)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) are energy efficient alternatives to commonly used deep neural networks (DNNs). Through event-driven information processing, SNNs can reduce the expensive compute requirements of DNNs considerably, while achieving comparable performance. However, high inference latency is a significant hindrance to the edge deployment of deep SNNs. Computation over multiple timesteps not only increases latency as well as overall energy budget due to higher number of operations, but also incurs memory access overhead of fetching membrane potentials, both of which lessen the energy benefits of SNNs. To overcome this bottleneck and leverage the full potential of SNNs, we propose an Iterative Initialization and Retraining method for SNNs (IIR-SNN) to perform single shot inference in the temporal axis. The method starts with an SNN trained with T timesteps (T>1). Then at each stage of latency reduction, the network trained at previous stage with higher timestep is utilized as initialization for subsequent training with lower timestep. This acts as a compression method, as the network is gradually shrunk in the temporal domain. In this paper, we use direct input encoding and choose T=5, since as per literature, it is the minimum required latency to achieve satisfactory performance on ImageNet. The proposed scheme allows us to obtain SNNs with up to unit latency, requiring a single forward pass during inference. We achieve top-1 accuracy of 93.05%, 70.15% and 67.71% on CIFAR-10, CIFAR-100 and ImageNet, respectively using VGG16, with just 1 timestep. In addition, IIR-SNNs perform inference with 5-2500X reduced latency compared to other state-of-the-art SNNs, maintaining comparable or even better accuracy. Furthermore, in comparison with standard DNNs, the proposed IIR-SNNs provide25-33X higher energy efficiency, while being comparable to them in classification performance.