Presentation
13 March 2024 From MicroLEDs to neuromorphic computing
Author Affiliations +
Abstract
GaN based microLED technology is particularly interesting for micro-displays for augmented reality. Beyond that, however, many additional applications exploiting the massively parallel nature of optical channels from microLED arrays are of interest. This includes microLED arrays for chip-based lensless microscopy, optogenetics, low power gas sensing, optical neuromorphic computing, high-speed maskless lithography or massively parallel line-of-sight communication in HPC centers (LIFI), replacing optical fibers. In order to drive large numbers of pixels at high frequencies in customized microLED arrays, the integration with a CMOS backplane chip is required. The talk will mostly focus on chip processing and hybrid integration techniques for microLEDs and the opportunities for GaN based photonic integration in general, and GaN/CMOS integration in particular. First applications of specially designed microLED arrays in the field of optical neuromorphic computing will also be discussed. Test results include pattern recognition of hand-written digits from the MNIST dataset.
Conference Presentation
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Andreas Waag, Steffen Bornemann, Georg Schöttler, Maximilian Vergin, Florian Meierhofer, Mayra Garcés-Schröder, Michael Fahrbach, Jana Hartmann, Robert Kraneis, Maximilian Müller, Noah Kaelin, and Christian Werner "From MicroLEDs to neuromorphic computing", Proc. SPIE PC12906, Light-Emitting Devices, Materials, and Applications XXVIII, PC129060G (13 March 2024); https://doi.org/10.1117/12.2692716
Advertisement
Advertisement
KEYWORDS
Gallium nitride

Optical computing

Maskless lithography

Microscopy

Optical communications

Optical fibers

Optical sensing

Back to Top