# Supervised Training of Siamese Spiking Neural Networks with Earth Mover's Distance

arXiv: https://arxiv.org/abs/2203.13207 · HTML: https://mlsanity.com/paper/2203.13207/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 20 Feb 2022.

## Builds on (most cited first, 9 of 9)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [Supervised learning based on temporal coding in spiking neural networks](https://mlsanity.com/paper/1606.08165/) (2016)
- [TristouNet: Triplet Loss for Speaker Turn Embedding](https://mlsanity.com/paper/1609.04301/) (2016)
- [Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems](https://mlsanity.com/paper/1311.0966/) (2013)
- [SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking](https://mlsanity.com/paper/2003.07584/) (2020)
- [Which spike train distance is most suitable for distinguishing rate and temporal coding?](https://mlsanity.com/paper/1708.07508/) (2017)

## Built on by (most cited first, 1 of 1)

- [Iteration over event space in time-to-first-spike spiking neural networks for Twitter bot classification](https://mlsanity.com/paper/2407.08746/) (2024)

## Abstract (arXiv)

This study adapts the highly-versatile siamese neural network model to the event data domain. We introduce a supervised training framework for optimizing Earth Mover's Distance (EMD) between spike trains with spiking neural networks (SNN). We train this model on images of the MNIST dataset converted into spiking domain with novel conversion schemes. The quality of the siamese embeddings of input images was evaluated by measuring the classifier performance for different dataset coding types. The models achieved performance similar to existing SNN-based approaches (F1-score of up to 0.9386) while using only about 15% of hidden layer neurons to classify each example. Furthermore, models which did not employ a sparse neural code were about 45% slower than their sparse counterparts. These properties make the model suitable for low energy consumption and low prediction latency applications.