Reservoir Computing with Boolean Logic Network Circuits

dc.contributor.advisorLathrop, Daniel Pen_US
dc.contributor.authorKomkov, Heidien_US
dc.contributor.departmentElectrical Engineeringen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2021-09-16T05:38:20Z
dc.date.available2021-09-16T05:38:20Z
dc.date.issued2021en_US
dc.description.abstractTo push the frontiers of machine learning, completely new computing architectures must be explored which efficiently use hardware resources. We test an unconventional use of digital logic gate circuits for reservoir computing, a machine learning algorithm that is used for rapid time series processing. In our approach, logic gates are configured into networks that can exhibit complex dynamics. Rather than the gates explicitly computing pre-programmed instructions, they are used collectively as a dynamical system that transforms input data into a higher dimensional representation. We probe the dynamics of such circuits using discrete components on a circuit board as well as an FPGA implementation. We show favorable machine learning performance, including radiofrequency classification accuracy comparableto a state of the art convolutional neural network with a fraction of the trainable parameters. Finally, we discuss the design and fabrication of a reservoir computing ASIC for high-speed time series processing.en_US
dc.identifierhttps://doi.org/10.13016/uesp-b6n8
dc.identifier.urihttp://hdl.handle.net/1903/27754
dc.language.isoenen_US
dc.subject.pqcontrolledArtificial intelligenceen_US
dc.subject.pqcontrolledElectrical engineeringen_US
dc.subject.pquncontrolledASICen_US
dc.subject.pquncontrolledboolean networksen_US
dc.subject.pquncontrolledFPGAen_US
dc.subject.pquncontrolledreservoir computingen_US
dc.titleReservoir Computing with Boolean Logic Network Circuitsen_US
dc.typeDissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Komkov_umd_0117E_21759.pdf
Size:
15.06 MB
Format:
Adobe Portable Document Format