Abstract
We demonstrate jointly-trained hybrid (optical-electronic) networks, where diffractive optical neural networks act as a trainable front-end mitigating the information loss at a low-resolution image sensor to improve the overall classification accuracy of the hybrid network.
© 2020 The Author(s)
PDF Article | Presentation VideoMore Like This
Jingxi Li, Deniz Mengu, Yi Luo, Yair Rivenson, and Aydogan Ozcan
SM1E.3 CLEO: Science and Innovations (CLEO:S&I) 2020
Yi Luo, Deniz Mengu, Nezih T. Yardimci, Yair Rivenson, Muhammed Veli, Mona Jarrahi, and Aydogan Ozcan
SM3F.7 CLEO: Science and Innovations (CLEO:S&I) 2020
Jun Rong Ong, Chin Chun Ooi, Thomas Y. L. Ang, Flynn Loh, Yu Xiang Peh, Soon Thor Lim, and Ching Eng Png
PsTh1F.2 Photonics in Switching and Computing (PS) 2020