Presentation
9 March 2021 Massively parallel amplitude-only Fourier neural network
Author Affiliations +
Abstract
Here we introduce a novel amplitude-only Fourier-optical processor paradigm capable of processing large-scale ~(1,000 × 1,000) matrices in a single time-step and 100 microsecond-short latency. We exemplary realize a convolutional neural network (CNN) performing classification tasks on 2-Megapixel large matrices at 10 kHz rates, which latency-outperforms current GPU and phase-based display technology by one and two orders of magnitude, respectively. Training this optical convolutional layer on image classification tasks and utilizing it in a hybrid optical-electronic CNN, shows classification accuracy of 98% (MNIST) and 54% (CIFAR-10).
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Volker J. Sorger "Massively parallel amplitude-only Fourier neural network", Proc. SPIE 11703, AI and Optical Data Sciences II, 117030B (9 March 2021); https://doi.org/10.1117/12.2585715
Advertisement
Advertisement
KEYWORDS
Neural networks

Display technology

Image classification

Matrices

Hybrid optics

Lenses

Liquid crystals

Back to Top