Integrated System-on-Module for Design-Space Exploration of Spiking Neural Networks
El-Masry M, Kourany T, Kho R, Werner T, Zjajo A, Weigel R (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: Institute of Electrical and Electronics Engineers Inc.
Conference Proceedings Title: AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding
Event location: Hangzhou, CHN
ISBN: 9798350332674
DOI: 10.1109/AICAS57966.2023.10168582
Abstract
We present an integrated system-on-module for design-space exploration of neurosynaptic behavior of complex, non-volatile memory enhanced, spiking neural networks. The system operates in a locally-analog, globally-digital manner, which enables both exploration and validation of individual computational components and characteristic spike-based features of neurosynaptic arrays. The system components are reconfigurable, adaptable and interchangeable enabling reproducible, precise firing patterns. The platform is coupled with an embedded resistive-RAM which acts as a weight retention mechanism. Experimental results obtained in 28 nm CMOS technology illustrate the feasibility of the methodology.
Authors with CRIS profile
Moamen El-Masry
Lehrstuhl für Technische Elektronik
Robert Weigel
Lehrstuhl für Technische Elektronik
Additional Organisation(s)
Involved external institutions
Infineon Technologies AG
Germany (DE)
Ferroelectric Memory GmbH
Germany (DE)
Innatera Nanosystems BV
Netherlands (NL)
Germany (DE)
Ferroelectric Memory GmbH
Germany (DE)
Innatera Nanosystems BV
Netherlands (NL)
How to cite
APA:
El-Masry, M., Kourany, T., Kho, R., Werner, T., Zjajo, A., & Weigel, R. (2023). Integrated System-on-Module for Design-Space Exploration of Spiking Neural Networks. In AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding. Hangzhou, CHN: Institute of Electrical and Electronics Engineers Inc..
MLA:
El-Masry, Moamen, et al. "Integrated System-on-Module for Design-Space Exploration of Spiking Neural Networks." Proceedings of the 5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023, Hangzhou, CHN Institute of Electrical and Electronics Engineers Inc., 2023.
BibTeX: Download