User: Guest  Login
Document type:
Konferenzbeitrag 
Author(s):
Etienne Mueller, Julius Hansjakob, Daniel Auge, Alois Knoll 
Title:
Minimizing Inference Time: Optimization Methods for Converted Deep Spiking Neural Networks 
Abstract:
Spiking neural networks offer the potential to drastically reduce energy consumption in edge devices. Unfortunately they are overshadowed by today’s common analog neural networks, whose superior backpropagation-based learning algorithms frequently demonstrate superhuman performance on different tasks. The best accuracies in spiking networks are achieved by training analog networks and converting them. Still, during runtime many simulation time steps are needed until they converge. To improve the...    »
 
Keywords:
Spiking Neural Networks, Conversion, Object Detection 
Book / Congress title:
International Joint Conference on Neural Networks (IJCNN) 
Congress (additional information):
accepted 
Year:
2021