# Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain

arXiv: https://arxiv.org/abs/1807.01013 · HTML: https://mlsanity.com/paper/1807.01013/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2018.

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

- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [GET: Group Event Transformer for Event-Based Vision](https://mlsanity.com/paper/2310.02642/) (2023)
- [Spiking Neural Networks for Frame-based and Event-based Single Object Localization](https://mlsanity.com/paper/2206.06506/) (2022)
- [Bina-Rep Event Frames: a Simple and Effective Representation for Event-based cameras](https://mlsanity.com/paper/2202.13662/) (2022)
- [Axonal Delay As a Short-Term Memory for Feed Forward Deep Spiking Neural Networks](https://mlsanity.com/paper/2205.02115/) (2022)
- [Spiking Neural Networks for event-based action recognition: A new task to understand their advantage](https://mlsanity.com/paper/2209.14915/) (2022)
- [A Comprehensive Review of Spiking Neural Networks: Interpretation, Optimization, Efficiency, and Best Practices](https://mlsanity.com/paper/2303.10780/) (2023)
- [An optimised deep spiking neural network architecture without gradients](https://mlsanity.com/paper/2109.12813/) (2021)
- [A New Look at Spike-Timing-Dependent Plasticity Networks for Spatio-Temporal Feature Learning](https://mlsanity.com/paper/2111.00791/) (2021)
- [Exploring the Limitations of Layer Synchronization in Spiking Neural Networks](https://mlsanity.com/paper/2408.05098/) (2024)
- [Enhancing SNN-based Spatio-Temporal Learning: A Benchmark Dataset and Cross-Modality Attention Model](https://mlsanity.com/paper/2410.15689/) (2024)
- [Event Transformer](https://mlsanity.com/paper/2204.05172/) (2022)
- [Energy-Aware FPGA Implementation of Spiking Neural Network with LIF Neurons](https://mlsanity.com/paper/2411.01628/) (2024)
- [LAND: A Longitudinal Analysis of Neuromorphic Datasets](https://mlsanity.com/paper/2602.15973/) (2026)
- [ANTShapes Benchmarking Datasets for Event-Based Neuromorphic Object Classification](https://mlsanity.com/paper/2608.27150/) (2026)

## Abstract (arXiv)

The advantage of spiking neural networks (SNNs) over their predecessors is their ability to spike, enabling them to use spike timing for coding and efficient computing. A neuromorphic dataset should allow a neuromorphic algorithm to clearly show that a SNN is able to perform better on the dataset than an ANN. We have analyzed both N-MNIST and N-Caltech101 along these lines, but focus our study on N-MNIST. First we evaluate if additional information is encoded in the time domain in a neuromoprhic dataset. We show that an ANN trained with backpropagation on frame based versions of N-MNIST and N-Caltech101 images achieve 99.23% and 78.01% accuracy. These are the best classification accuracies obtained on these datasets to date. Second we present the first unsupervised SNN to be trained on N-MNIST and demonstrate results of 91.78%. We also use this SNN for further experiments on N-MNIST to show that rate based SNNs perform better, and precise spike timings are not important in N-MNIST. N-MNIST does not, therefore, highlight the unique ability of SNNs. The conclusion of this study opens an important question in neuromorphic engineering - what, then, constitutes a good neuromorphic dataset?