Presentation
9 March 2020 Integration of diffractive optical neural networks with electronic neural networks (Conference Presentation)
Author Affiliations +
Abstract
We demonstrate significant improvements in the inference accuracy of diffractive optical neural networks and report that a five-layer, phase-only (or amplitude/phase) modulation diffractive network can achieve 97.18% (97.81%) and 89.13% (89.32%) blind-testing accuracy for MNIST and Fashion-MNIST datasets, respectively. Moreover, the integration of diffractive neural networks with electronic deep neural networks is investigated. Using a single fully-connected layer on the electronic part and a five-layer, phase-only diffractive neural network at the optical front-end, we achieved blind-testing accuracies of 98.71% and 90.04% for MNIST and Fashion-MNIST datasets, respectively, despite a >7.8-fold reduction in the number of pixels at the opto-electronic sensor-array.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Aydogan Ozcan, Deniz Mengu, Yi Luo, Yair Rivenson, and Jingxi Li "Integration of diffractive optical neural networks with electronic neural networks (Conference Presentation)", Proc. SPIE 11284, Smart Photonic and Optoelectronic Integrated Circuits XXII, 112841X (9 March 2020); https://doi.org/10.1117/12.2547200
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
KEYWORDS
Neural networks

Integrated optics

Optical networks

Machine learning

Modulation

Optoelectronics

Sensors

Back to Top