An optical diffractive deep neural network with multiple frequency-channels
This work addresses the need for more accurate optical neural networks, which could enable faster, energy-efficient AI applications, though it appears incremental as it builds on existing diffractive network concepts.
The paper tackles the problem of improving the accuracy of diffractive deep neural networks (DNNets), which are optical machine learning frameworks that operate at light speed with no power consumption, by introducing multiple frequency-channels in each layer, and the result is a significant accuracy increase on fashion-MNIST and EMNIST datasets.
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.