PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
We report the use of ensemble learning to achieve significant improvements in the performance of diffractive optical classifiers on CIFAR-10 image dataset. We initially created a pool of 1252 diversely-trained diffractive network models; using a novel iterative pruning algorithm, we trimmed this down to an ensemble size of 14 diffractive networks to achieve a blind testing accuracy of 61.14% on CIFAR-10 image classification, which performs >16% higher in its inference accuracy compared to the average performance of the individual diffractive networks within the ensemble. These results signify a major advancement in all-optical inference and image classification capabilities of diffractive networks.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Md Sadman Sakib Rahman, Jingxi Li, Deniz Mengu, Yair Rivenson, Aydogan Ozcan, "Advancing diffractive network-based image classification by ensemble learning," Proc. SPIE PC12019, AI and Optical Data Sciences III, PC1201901 (9 March 2022); https://doi.org/10.1117/12.2608016