Spiking neural networks (SNNs) operating on neuromorphic hardware can enable cognitive functionality with relatively low power consumption as compared to other artificial neural network implementations, making it ideally suited for resource-constrained space platforms such as CubeSats. The objective of this study is to investigate the implementation of a modulation recognition capability using SNNs, which may eventually be applied to neuromorphic hardware for implementation. This preliminary analysis uses a software simulation approach with an unsupervised learning algorithm based on spike-timing-dependent plasticity for classification of digital modulation constellation patterns. This modulation recognition capability can provide enhanced situational awareness for a space platform and facilitate additional high-level cognitive functionality that can be investigated in future studies.
Investigation of Spiking Neural Networks for Modulation Recognition using Spike-Timing-Dependent Plasticity
01.06.2019
847533 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Cognitive processing using spiking neural networks
IEEE | 2009
|Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition
British Library Online Contents | 2015
|Dilute Combustion Control Using Spiking Neural Networks
British Library Conference Proceedings | 2021
|