# Simple and complex spiking neurons: perspectives and analysis in a simple STDP scenario

arXiv: https://arxiv.org/abs/2207.04881 · HTML: https://mlsanity.com/paper/2207.04881/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 90 references that are in the map.
- First posted on arXiv 28 Jun 2022.

## Builds on (most cited first, 16 of 16)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Efficient Neuromorphic Signal Processing with Loihi 2](https://mlsanity.com/paper/2111.03746/) (2021)
- [A Survey of Neuromorphic Computing and Neural Networks in Hardware](https://mlsanity.com/paper/1705.06963/) (2017)
- [Supervised learning based on temporal coding in spiking neural networks](https://mlsanity.com/paper/1606.08165/) (2016)
- [Spiking Deep Networks with LIF Neurons](https://mlsanity.com/paper/1510.08829/) (2015)
- [Fast and energy-efficient neuromorphic deep learning with first-spike times](https://mlsanity.com/paper/1912.11443/) (2019)
- [SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron](https://mlsanity.com/paper/1903.02440/) (2019)
- [First-spike based visual categorization using reward-modulated STDP](https://mlsanity.com/paper/1705.09132/) (2017)
- [Comparison of non-linear activation functions for deep neural networks on MNIST classification task](https://mlsanity.com/paper/1804.02763/) (2018)
- [Keys to Accurate Feature Extraction Using Residual Spiking Neural Networks](https://mlsanity.com/paper/2111.05955/) (2021)
- [Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks](https://mlsanity.com/paper/1901.02671/) (2019)
- [Accelerated Analog Neuromorphic Computing](https://mlsanity.com/paper/2003.11996/) (2020)
- [An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture](https://mlsanity.com/paper/1804.01906/) (2018)
- [Unsupervised Spiking Instance Segmentation on Event Data using STDP](https://mlsanity.com/paper/2111.05283/) (2021)

## Built on by (most cited first, 6 of 6)

- [Spiking Neural Networks for event-based action recognition: A new task to understand their advantage](https://mlsanity.com/paper/2209.14915/) (2022)
- [Hybrid Spiking Neural Network Fine-tuning for Hippocampus Segmentation](https://mlsanity.com/paper/2302.07328/) (2023)
- [Augmenting learning in neuro-embodied systems through neurobiological first principles](https://mlsanity.com/paper/2407.04525/) (2024)
- [STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networks](https://mlsanity.com/paper/2411.11082/) (2024)
- [Fundamental Survey on Neuromorphic Based Audio Classification](https://mlsanity.com/paper/2502.15056/) (2025)
- [Frameworks for SNNs: a Review of Data Science-oriented Software and an Expansion of SpykeTorch](https://mlsanity.com/paper/2302.07624/) (2023)

## Abstract (arXiv)

Spiking neural networks (SNNs) are largely inspired by biology and neuroscience and leverage ideas and theories to create fast and efficient learning systems. Spiking neuron models are adopted as core processing units in neuromorphic systems because they enable event-based processing. The integrate-and-fire (I&F) models are often adopted, with the simple Leaky I&F (LIF) being the most used. The reason for adopting such models is their efficiency and/or biological plausibility. Nevertheless, rigorous justification for adopting LIF over other neuron models for use in artificial learning systems has not yet been studied. This work considers various neuron models in the literature and then selects computational neuron models that are single-variable, efficient, and display different types of complexities. From this selection, we make a comparative study of three simple I&F neuron models, namely the LIF, the Quadratic I&F (QIF) and the Exponential I&F (EIF), to understand whether the use of more complex models increases the performance of the system and whether the choice of a neuron model can be directed by the task to be completed. Neuron models are tested within an SNN trained with Spike-Timing Dependent Plasticity (STDP) on a classification task on the N-MNIST and DVS Gestures datasets. Experimental results reveal that more complex neurons manifest the same ability as simpler ones to achieve high levels of accuracy on a simple dataset (N-MNIST), albeit requiring comparably more hyper-parameter tuning. However, when the data possess richer Spatio-temporal features, the QIF and EIF neuron models steadily achieve better results. This suggests that accurately selecting the model based on the richness of the feature spectrum of the data could improve the whole system's performance. Finally, the code implementing the spiking neurons in the SpykeTorch framework is made publicly available.