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.

翻译：这项研究将高逆向的 Siamese 神经网络模型与事件数据域相适应。 我们引入了一个受监督的培训框架, 以优化带有喷射神经网络的顶点列之间的地球移动器距离(EMD ) 。 我们用新转换方案对MNIST数据集转换成喷射域的图像进行这种模型培训。 通过测量分类器在不同数据集编码类型中的性能,评估了输入图像嵌入系统的质量。 这些模型取得了类似于基于 SNN 的现有方法的性能( F1 点,最高为 0.9386), 仅使用约15%的隐性层神经元进行分类。 此外, 没有使用稀薄神经编码的模型比其稀少的神经编码大约慢45%。 这些特性使得模型适合低能量消耗和低预测耐久性应用。