Jinfeng Zhu

Yingshi Chen, Jinfeng Zhu

Diffractive deep neural network (DNNet) is a novel machine learning framework on the modulation of optical transmission. Diffractive network would get predictions at the speed of light. It's pure passive architecture, no additional power consumption. We improved the accuracy of diffractive network with optical waves at different frequency. Each layers have multiple frequency-channels (optical distributions at different frequency). These channels are merged at the output plane to get final output. The experiment in the fasion-MNIST and EMNIST datasets showed multiple frequency-channels would increase the accuracy a lot. We also give detailed analysis to show the difference between DNNet and MLP. The modulation process in DNNet is actually optical activation function. We develop an open source package ONNet. The source codes are available at https://github.com/closest-git/ONNet.

Yingshi Chen, Jinfeng Zhu

The design of surface plasmon polaritons (SPP) films is an ill-posed inverse problem. There are many-to-one correspondence between the structures and user needs. We present a novel guided deep learning algorithm to find optimal solutions (with both high accuracy and low cost). To achieve this goal, we use low cost sample replacement algorithm in training process. The deep CNN would gradually learn better model from samples with lower cost. We have successfully applied this algorithm to the design of low-cost SPP films. Our model learned to replace precious metals with ordinary metals to reduce cost. So the the cost of predicted structure is much lower than standard deep CNN. And the average relative error of spectrum is less than 10%. The source codes are available at https://github.com/closest-git/MetaLab.