Details

Autor(en) / Beteiligte

• Pabian, Mateusz
• Rzepka, Dominik
• Pawlak, Miroslaw

Titel

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

Ist Teil von

• ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, p.4233-4237

Ort / Verlag

IEEE

Erscheinungsjahr

2022

Link zum Volltext

• IEEE_Xplore

Quelle

IEEE Explore

Beschreibungen/Notizen

• 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.