Supervised Training of Siamese Spiking Neural Networks with Earth Mover's Distance
This work addresses low energy consumption and low prediction latency applications in neuromorphic computing, but it is incremental as it adapts existing siamese models to spiking neural networks with specific optimizations.
The study tackled the problem of adapting siamese neural networks to event data by introducing a supervised training framework that optimizes Earth Mover's Distance between spike trains with spiking neural networks, achieving an F1-score of up to 0.9386 on MNIST while using only about 15% of hidden layer neurons.
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.