Spiking Neural Networks Design-Space Exploration Platform Supporting Online and Offline Learning
El-Masry M, Anees S, Weigel R (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: IEEE Computer Society
Book Volume: 2023-September
Conference Proceedings Title: International System on Chip Conference
Event location: Santa Clara, CA
ISBN: 9798350300116
DOI: 10.1109/SOCC58585.2023.10257044
Abstract
As Spiking Neural Networks (SNNs) gain popularity, more SNN components are developed. SNN development requires a dedicated platform for testing and evaluating the various network components. This paper presents a novel system-on-module (SoM) for exploring spiking neural network hardware components based on a fully integrated platform. The platform is highly reconfigurable, allowing different modes of operation for SNN on/offline learning. The proposed fully integrated SoM platform was tested for its ability to perform learning recognition of random input patterns using the STDP learning algorithm. The results obtained using 28 nm CMOS technology demonstrate the feasibility of this approach.
Authors with CRIS profile
Additional Organisation(s)
Involved external institutions
Germany (DE)How to cite
APA:
El-Masry, M., Anees, S., & Weigel, R. (2023). Spiking Neural Networks Design-Space Exploration Platform Supporting Online and Offline Learning. In Jurgen Becker, Andrew Marshall, Tanja Harbaum, Amlan Ganguly, Fahad Siddiqui, Kieran McLaughlin (Eds.), International System on Chip Conference. Santa Clara, CA, US: IEEE Computer Society.
MLA:
El-Masry, Moamen, Sohaib Anees, and Robert Weigel. "Spiking Neural Networks Design-Space Exploration Platform Supporting Online and Offline Learning." Proceedings of the 36th IEEE International System-on-Chip Conference, SOCC 2023, Santa Clara, CA Ed. Jurgen Becker, Andrew Marshall, Tanja Harbaum, Amlan Ganguly, Fahad Siddiqui, Kieran McLaughlin, IEEE Computer Society, 2023.
BibTeX: Download