ClassONN: Classification with Oscillatory Neural Networks using the Kuramoto Model

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

272 Downloads (Pure)


Over the recent years, networks of coupled oscillators or oscillatory neural networks (ONNs) emerged as an alternative computing paradigm with information encoded in phase. Such networks are intrinsically attractive for associative memory applications such as pattern retrieval. Thus far, there are few works focusing on image classification using ONNs, as there is no straightforward way to do it. This paper investigates the performance of a neuromorphic phase-based classification model using a fully connected single layer ONNs. For benchmarking, we deploy the ONN on the full set of 28×28 binary MNIST handwritten digits and achieve around 70% accuracy on both training and test set. To the best of our knowledge, this is the first effort classifying such large images utilizing ONNs.
Originele taal-2Engels
Titel2024 Design, Automation & Test in Europe Conference & Exhibition, DATE 2024
UitgeverijInstitute of Electrical and Electronics Engineers
Aantal pagina's2
ISBN van elektronische versie978-3-9819263-8-5
StatusGepubliceerd - 10 jun. 2024
EvenementDesign, Automation, Test in Europe (DATE) 2024 - Valencia, Spanje
Duur: 25 mrt. 202427 mrt. 2024


CongresDesign, Automation, Test in Europe (DATE) 2024



Niet toegevoegd101092096


    Duik in de onderzoeksthema's van 'ClassONN: Classification with Oscillatory Neural Networks using the Kuramoto Model'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit