Presentation
17 March 2023 Image sensing with multilayer nonlinear optical neural networks
Author Affiliations +
Proceedings Volume PC12438, AI and Optical Data Sciences IV; PC124380M (2023) https://doi.org/10.1117/12.2650289
Event: SPIE OPTO, 2023, San Francisco, California, United States
Abstract
Linear optics has been long applied to image compression. However, it is widely known that nonlinear neural networks outperform linear models in terms of feature extraction and image compression. Here, we show a nonlinear multilayer optical neural network using a commercially available image intensifier as a scalable optical-to-optical nonlinear activation function. We experimentally demonstrated that nonlinear ONNs outperform linear optical linear encoders in a variety of non-trivial machine vision tasks at a high image compression ratio (up to 800:1). We have shown that nonlinear ONNs can directly process optical inputs from physical objects under natural illumination, which provides a new pathway towards high-volume, high-throughput, and low-latency machine vision processing.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tianyu Wang, Mandar M. Sohoni, Logan G. Wright, Tatsuhiro Onodera, Shi-Yuan Ma, Maxwell Anderson, and Peter L. McMahon "Image sensing with multilayer nonlinear optical neural networks", Proc. SPIE PC12438, AI and Optical Data Sciences IV, PC124380M (17 March 2023); https://doi.org/10.1117/12.2650289
Advertisement
Advertisement
KEYWORDS
Neural networks

Nonlinear optics

Computer programming

Image compression

Machine vision

Image classification

Image sensors

Back to Top