# Towards Understanding the Effect of Leak in Spiking Neural Networks

arXiv: https://arxiv.org/abs/2006.08761 · HTML: https://mlsanity.com/paper/2006.08761/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 15 of 15)

- [Fully neuromorphic vision and control for autonomous drone flight](https://mlsanity.com/paper/2303.08778/) (2023)
- [Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks](https://mlsanity.com/paper/2104.12528/) (2021)
- [Spiking Neural Networks for Frame-based and Event-based Single Object Localization](https://mlsanity.com/paper/2206.06506/) (2022)
- [Spiking Neural Networks for event-based action recognition: A new task to understand their advantage](https://mlsanity.com/paper/2209.14915/) (2022)
- [Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules](https://mlsanity.com/paper/2111.07785/) (2021)
- [Noise-Robust Deep Spiking Neural Networks with Temporal Information](https://mlsanity.com/paper/2104.11169/) (2021)
- [Best of Both Worlds: Hybrid SNN-ANN Architecture for Event-based Optical Flow Estimation](https://mlsanity.com/paper/2306.02960/) (2023)
- [Timing-Based Backpropagation in Spiking Neural Networks Without Single-Spike Restrictions](https://mlsanity.com/paper/2211.16113/) (2022)
- [HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds](https://mlsanity.com/paper/2308.10373/) (2023)
- [MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization](https://mlsanity.com/paper/2511.12199/) (2025)
- [Parallel Hyperparameter Optimization Of Spiking Neural Network](https://mlsanity.com/paper/2403.00450/) (2024)
- [Understanding the Functional Roles of Modelling Components in Spiking Neural Networks](https://mlsanity.com/paper/2403.16674/) (2024)
- [Spike-TBR: a Noise Resilient Neuromorphic Event Representation](https://mlsanity.com/paper/2506.04817/) (2025)
- [SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks](https://mlsanity.com/paper/2509.22581/) (2025)
- [SRAM-Based Compute-in-Memory Accelerator for Linear-decay Spiking Neural Networks](https://mlsanity.com/paper/2603.12739/) (2026)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) are being explored to emulate the astounding capabilities of human brain that can learn and compute functions robustly and efficiently with noisy spiking activities. A variety of spiking neuron models have been proposed to resemble biological neuronal functionalities. With varying levels of bio-fidelity, these models often contain a leak path in their internal states, called membrane potentials. While the leaky models have been argued as more bioplausible, a comparative analysis between models with and without leak from a purely computational point of view demands attention. In this paper, we investigate the questions regarding the justification of leak and the pros and cons of using leaky behavior. Our experimental results reveal that leaky neuron model provides improved robustness and better generalization compared to models with no leak. However, leak decreases the sparsity of computation contrary to the common notion. Through a frequency domain analysis, we demonstrate the effect of leak in eliminating the high-frequency components from the input, thus enabling SNNs to be more robust against noisy spike-inputs.