# BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning

arXiv: https://arxiv.org/abs/2007.04039 · HTML: https://mlsanity.com/paper/2007.04039/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 24 of 24)

- [Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies](https://mlsanity.com/paper/2304.12760/) (2023)
- [Quantized Spike-driven Transformer](https://mlsanity.com/paper/2501.13492/) (2025)
- [Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity](https://mlsanity.com/paper/2111.01760/) (2021)
- [Q-SNNs: Quantized Spiking Neural Networks](https://mlsanity.com/paper/2406.13672/) (2024)
- [The fine line between dead neurons and sparsity in binarized spiking neural networks](https://mlsanity.com/paper/2201.11915/) (2022)
- [Spike time displacement based error backpropagation in convolutional spiking neural networks](https://mlsanity.com/paper/2108.13621/) (2021)
- [An Encoding Framework for Binarized Images using HyperDimensional Computing](https://mlsanity.com/paper/2312.00454/) (2023)
- [Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism](https://mlsanity.com/paper/2502.14344/) (2025)
- [Navigating Local Minima in Quantized Spiking Neural Networks](https://mlsanity.com/paper/2202.07221/) (2022)
- [Low Precision Quantization-aware Training in Spiking Neural Networks with Differentiable Quantization Function](https://mlsanity.com/paper/2305.19295/) (2023)
- [Sparse-firing regularization methods for spiking neural networks with time-to-first spike coding](https://mlsanity.com/paper/2307.13007/) (2023)
- [Models Developed for Spiking Neural Networks](https://mlsanity.com/paper/2212.04377/) (2022)
- [BSO: Binary Spiking Online Optimization Algorithm](https://mlsanity.com/paper/2511.12502/) (2025)
- [A brain basis of dynamical intelligence for AI and computational neuroscience](https://mlsanity.com/paper/2105.07284/) (2021)
- [Effects of VLSI Circuit Constraints on Temporal-Coding Multilayer Spiking Neural Networks](https://mlsanity.com/paper/2106.10382/) (2021)
- [Spiking neural networks trained via proxy](https://mlsanity.com/paper/2109.13208/) (2021)
- [S3NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networks](https://mlsanity.com/paper/2201.10879/) (2022)
- [Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Efficient Weight Quantization](https://mlsanity.com/paper/2409.15849/) (2024)
- [Equivalence of approximation by networks of single- and multi-spike neurons](https://mlsanity.com/paper/2603.13478/) (2026)
- [An FPGA-Based SoC Architecture with a RISC-V Controller for Energy-Efficient Temporal-Coding Spiking Neural Networks](https://mlsanity.com/paper/2603.18054/) (2026)
- [Binary Spiking Neural Networks as Causal Models](https://mlsanity.com/paper/2604.27007/) (2026)
- [Exploring Tradeoffs in Spiking Neural Networks](https://mlsanity.com/paper/2212.09500/) (2022)
- [Robust Iterative Value Conversion: Deep Reinforcement Learning for Neurochip-driven Edge Robots](https://mlsanity.com/paper/2408.13018/) (2024)
- [A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks](https://mlsanity.com/paper/2508.12609/) (2025)

## Abstract (arXiv)

We recently proposed the S4NN algorithm, essentially an adaptation of backpropagation to multilayer spiking neural networks that use simple non-leaky integrate-and-fire neurons and a form of temporal coding known as time-to-first-spike coding. With this coding scheme, neurons fire at most once per stimulus, but the firing order carries information. Here, we introduce BS4NN, a modification of S4NN in which the synaptic weights are constrained to be binary (+1 or -1), in order to decrease memory (ideally, one bit per synapse) and computation footprints. This was done using two sets of weights: firstly, real-valued weights, updated by gradient descent, and used in the backward pass of backpropagation, and secondly, their signs, used in the forward pass. Similar strategies have been used to train (non-spiking) binarized neural networks. The main difference is that BS4NN operates in the time domain: spikes are propagated sequentially, and different neurons may reach their threshold at different times, which increases computational power. We validated BS4NN on two popular benchmarks, MNIST and Fashion-MNIST, and obtained reasonable accuracies for this sort of network (97.0% and 87.3% respectively) with a negligible accuracy drop with respect to real-valued weights (0.4% and 0.7%, respectively). We also demonstrated that BS4NN outperforms a simple BNN with the same architectures on those two datasets (by 0.2% and 0.9% respectively), presumably because it leverages the temporal dimension. The source codes of the proposed BS4NN are publicly available at https://github.com/SRKH/BS4NN.