RSS icon
Twitter icon
Facebook icon
Vimeo icon
YouTube icon

RF Signal Classification using Boolean Reservoir Computing on an FPGA

TitleRF Signal Classification using Boolean Reservoir Computing on an FPGA
Publication TypeConference Paper
Year of Publication2021
AuthorsH. Komkov, L. Pocher, A. Restelli, B. Hunt, and D. Lathrop
Conference Name2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
PublisherInt Neural Network Soc; IEEE Computat Intelligence Soc
ISBN Number978-0-7381-3366-9
KeywordsBoolean networks, FPGA, hardware acceleration, reservoir computing, RF classification
Abstract

Networks of Boolean logic gates exhibiting complex dynamical behavior are promising reservoirs for hardware-accelerated reservoir computing. Using an FPGA, we explore the parameter space of both clocked and unclocked Boolean networks, and identify configurations that are suitable for information processing. We use an FPGA-based reservoir to process a subset of the DeepSig 2016 dataset, showing classification accuracy using logistic regression competitive with a state-of-the-art convolutional neural network, achieved with a fraction of the trainable parameters.

DOI10.1109/IJCNN52387.2021.9533342