Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks

Kugele A, Pfeil T, Pfeiffer M, Chicca E (2020)
Frontiers in Neuroscience 14: 439.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
OA 719.29 KB
Autor*in
Kugele, Alexander; Pfeil, Thomas; Pfeiffer, Michael; Chicca, ElisabettaUniBi
Abstract / Bemerkung
Spiking neural networks (SNNs) are potentially highly efficient models for inference on fully parallel neuromorphic hardware, but existing training methods that convert conventional artificial neural networks (ANNs) into SNNs are unable to exploit these advantages. Although ANN-to-SNN conversion has achieved state-of-the-art accuracy for static image classification tasks, the following subtle but important difference in the way SNNs and ANNs integrate information over time makes the direct application of conversion techniques for sequence processing tasks challenging. Whereas all connections in SNNs have a certain propagation delay larger than zero, ANNs assign different roles to feed-forward connections, which immediately update all neurons within the same time step, and recurrent connections, which have to be rolled out in time and are typically assigned a delay of one time step. Here, we present a novel method to obtain highly accurate SNNs for sequence processing by modifying the ANN training before conversion, such that delays induced by ANN rollouts match the propagation delays in the targeted SNN implementation. Our method builds on the recently introduced framework of streaming rollouts, which aims for fully parallel model execution of ANNs and inherently allows for temporal integration by merging paths of different delays between input and output of the network. The resulting networks achieve state-of-the-art accuracy for multiple event-based benchmark datasets, including N-MNIST, CIFAR10-DVS, N-CARS, and DvsGesture, and through the use of spatio-temporal shortcut connections yield low-latency approximate network responses that improve over time as more of the input sequence is processed. In addition, our converted SNNs are consistently more energy-efficient than their corresponding ANNs.
Erscheinungsjahr
2020
Zeitschriftentitel
Frontiers in Neuroscience
Band
14
Art.-Nr.
439
eISSN
1662-453X
Finanzierungs-Informationen
Open-Access-Publikationskosten wurden durch die Deutsche Forschungsgemeinschaft und die Universität Bielefeld gefördert.
Page URI
https://pub.uni-bielefeld.de/record/2943400

Zitieren

Kugele A, Pfeil T, Pfeiffer M, Chicca E. Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks. Frontiers in Neuroscience. 2020;14: 439.
Kugele, A., Pfeil, T., Pfeiffer, M., & Chicca, E. (2020). Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks. Frontiers in Neuroscience, 14, 439. doi:10.3389/fnins.2020.00439
Kugele, A., Pfeil, T., Pfeiffer, M., and Chicca, E. (2020). Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks. Frontiers in Neuroscience 14:439.
Kugele, A., et al., 2020. Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks. Frontiers in Neuroscience, 14: 439.
A. Kugele, et al., “Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks”, Frontiers in Neuroscience, vol. 14, 2020, : 439.
Kugele, A., Pfeil, T., Pfeiffer, M., Chicca, E.: Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks. Frontiers in Neuroscience. 14, : 439 (2020).
Kugele, Alexander, Pfeil, Thomas, Pfeiffer, Michael, and Chicca, Elisabetta. “Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks”. Frontiers in Neuroscience 14 (2020): 439.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2020-05-15T11:22:59Z
MD5 Prüfsumme
20f69a88a7ae98366f54ab2cdbc03b0d

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 32431592
PubMed | Europe PMC

Suchen in

Google Scholar