Supervised Training of Siamese Spiking Neural Networks with Earth's Mover Distance
share
This study adapts the highly-versatile siamese neural network model to the event data domain. We introduce a supervised training framework for optimizing Earth's Mover 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 models which did not employ a sparse neural code were about 45 their sparse counterparts. These properties make the model suitable for low energy consumption and low prediction latency applications.
READ FULL TEXT