Building energy-efficient edge AI hardware through lessons from neuromorphic computing
PhD defence, Friday 9 October 2026, Simon Niklas Richter
During his PhD, Simon Richter investigated how increasingly capable AI models can move from the cloud to battery-powered edge devices, and how lessons from the remarkable efficiency of biological brains can guide hardware design under tight energy, latency, and silicon area constraints to this end.
Grounded in neuromorphic computing, he developed model optimization and compression techniques that drastically reduce computational and data movement cost of modern AI systems, leading to larger more capable models previously being constrained to larger scale GPU or cloud deployment to be deployed on the edge at mW power budgets, demonstrated in two fabricated accelerator chips in advanced CMOS nodes.
The PhD study was completed at the Department of Electrical and Computer Engineering, Aarhus University.
This summary was prepared by the PhD student.
Time: Friday, 9 October 2026 at 14:00
Place: Aarhus Univeristy, Finlandsgade 22, building 5125, room 417, 8200 Aarhus N.
Title of PhD thesis: Energy-efficient Hardware Accelerator Design for the Edge through Lessons from Neuromorphic Computing
Contact information: Simon Niklas Richter, e-mail: siri@ece.au.dk, tel.: +45 50394460
Members of the assessment committee:
(Chair) Lektor Christian Fisher Pedersen, Aarhus University, Denmark
Professor Kaushik Roy, Purdue University, Purdue University, USA
Professor Henk Corporaal, Eindhoven University of Technology, The Netherlands
Main supervisor: Professor Farshad Moradi, Department of Electrical and Computer Engineering, Aarhus University, Denmark
Language: The PhD dissertation will be defended in English
The defence is public.
The PhD thesis is available for reading at the Graduate School of Technical Sciences/GSTS, Ny Munkegade 120, building 1521, 8000 Aarhus C.