# Efficient Spiking Neural Networks with Radix Encoding

arXiv: https://arxiv.org/abs/2105.06943 · HTML: https://mlsanity.com/paper/2105.06943/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2021.

## Built on by (most cited first, 12 of 12)

- [Advancing Spiking Neural Networks towards Deep Residual Learning](https://mlsanity.com/paper/2112.08954/) (2021)
- [Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection](https://mlsanity.com/paper/2306.12010/) (2023)
- [Differential Coding for Training-Free ANN-to-SNN Conversion](https://mlsanity.com/paper/2503.00301/) (2025)
- [On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments](https://mlsanity.com/paper/2307.11242/) (2023)
- [DeepFire2: A Convolutional Spiking Neural Network Accelerator on FPGAs](https://mlsanity.com/paper/2305.05187/) (2023)
- [A Resource-efficient Spiking Neural Network Accelerator Supporting Emerging Neural Encoding](https://mlsanity.com/paper/2206.02495/) (2022)
- [Highly Efficient SNNs for High-speed Object Detection](https://mlsanity.com/paper/2309.15883/) (2023)
- [Optimizing for In-memory Deep Learning with Emerging Memory Technology](https://mlsanity.com/paper/2112.00324/) (2021)
- [Error Amplification Limits ANN-to-SNN Conversion in Continuous Control](https://mlsanity.com/paper/2601.21778/) (2026)
- [Desire Backpropagation: A Lightweight Training Algorithm for Multi-Layer Spiking Neural Networks based on Spike-Timing-Dependent Plasticity](https://mlsanity.com/paper/2211.05412/) (2022)
- [When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networks](https://mlsanity.com/paper/2312.06900/) (2023)
- [Sparsity-Aware Hardware-Software Co-Design of Spiking Neural Networks: An Overview](https://mlsanity.com/paper/2408.14437/) (2024)

## Abstract (arXiv)

Spiking neural networks (SNNs) have advantages in latency and energy efficiency over traditional artificial neural networks (ANNs) due to its event-driven computation mechanism and replacement of energy-consuming weight multiplications with additions. However, in order to reach accuracy of its ANN counterpart, it usually requires long spike trains to ensure the accuracy. Traditionally, a spike train needs around one thousand time steps to approach similar accuracy as its ANN counterpart. This offsets the computation efficiency brought by SNNs because longer spike trains mean a larger number of operations and longer latency. In this paper, we propose a radix encoded SNN with ultra-short spike trains. In the new model, the spike train takes less than ten time steps. Experiments show that our method demonstrates 25X speedup and 1.1% increment on accuracy, compared with the state-of-the-art work on VGG-16 network architecture and CIFAR-10 dataset.