KIT | KIT-Bibliothek | Impressum | Datenschutz

Analog Printed Spiking Neuromorphic Circuit

Pal, Priyanjana ORCID iD icon 1; Zhao, Haibin ORCID iD icon 2; Shatta, Maha 1; Hefenbrock, Michael; Mamaghani, Sina B. 1; Nassif, Sani; Beigl, Michael ORCID iD icon 2; B. Tahoori, Mehdi 1
1 Institut für Technische Informatik (ITEC), Karlsruher Institut für Technologie (KIT)
2 Institut für Telematik (TM), Karlsruher Institut für Technologie (KIT)

Abstract:

Biologically-inspired Spiking Neural Networks have emerged as a promising avenue for energy-efficient, high-performance neuromorphic computing. With the demand for highly-customized and cost-effective solutions in emerging application domains like soft robotics, wearables, or IoT-devices, Printed Electronics has emerged as an alternative to traditional silicon technologies leveraging soft materials and flexible substrates. In this paper, we propose an energy-efficient analog printed spiking neuromorphic circuit and a corresponding learning algorithm. Simulations on 13 benchmark datasets show an average of 3.86× power improvement with similar classification accuracy compared to previous works.


Preprint §
DOI: 10.5445/IR/1000167509
Veröffentlicht am 22.01.2024
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Technische Informatik (ITEC)
Institut für Telematik (TM)
Publikationstyp Proceedingsbeitrag
Publikationsdatum 27.03.2024
Sprache Englisch
Identifikator KITopen-ID: 1000167509
Erschienen in 2024 Design, Automation and Test in Europe Conference (DATE)
Veranstaltung 27th Design, Automation and Test in Europe Conference (DATE 2024), Valencia, Spanien, 25.03.2024 – 27.03.2024
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Seiten 6 S.
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page