Translator Disclaimer
Presentation
21 August 2020 Class-specific differential detection improves the inference accuracy of diffractive optical neural networks
Author Affiliations +
Abstract
We report new design strategies to increase the inference accuracy of Diffractive Deep Neural Networks (D2NNs). Using a differential detection scheme that is combined with the joint-training of multiple D2NNs, each specialized on a single object-class, D2NN-based all-optical classification systems numerically achieve blind-testing accuracies of 98.52%, 91.48% and 50.82% for MNIST, Fashion-MNIST and grayscale CIFAR-10 datasets, respectively. Furthermore, using three independently-trained D2NNs that project their light onto a common output plane enables the system to achieve 98.59%, 91.06% and 51.44%, respectively. Through these systematic improvements, the reported blind-inference performance sets the state-of-the-art for an all-optical neural network design.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jingxi Li, Deniz Mengu, Yi Luo, Yair Rivenson, and Aydogan Ozcan "Class-specific differential detection improves the inference accuracy of diffractive optical neural networks", Proc. SPIE 11469, Emerging Topics in Artificial Intelligence 2020, 114691A (21 August 2020); https://doi.org/10.1117/12.2567467
PROCEEDINGS
PRESENTATION


SHARE
Advertisement
Advertisement
Back to Top