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

• Published in: Frontiers in neuroscience Vol. 14; p. 439
• Main Authors: Kugele, Alexander, Pfeil, Thomas, Pfeiffer, Michael, Chicca, Elisabetta
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 05.05.2020; Frontiers Media S.A
• Subjects: Classification; efficient inference; event-based vision; Firing pattern; Information processing; Latency; Neural networks; neuromorphic computing; Neurons; Neuroscience; sequence processing; spiking neural networks; spiking neural networks; efficient inference; event-based vision; neuromorphic computing; sequence processing

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...