Multi-Task Learning by Multi-Wave Optical Diffractive Network
Recently, there has been tremendous researches in Optical neural networks that could complete comparatively complex computation by optical characteristic with much more fewer dissipation than electrical networks. Existed neural networks based on the optical circuit are structured with an optical grating platform with different diffractive phase at different diffractive points. In this study, it proposed a multi-wave deep diffractive network with approximately 106 synapses, and it is easy to make hardware implementation of neuromorphic networks. In the optical architecture, it can utilize optical diffractive characteristic and different wavelengths to perform different tasks. Different wavelengths and different tasks inputs are independent of each other. Moreover, we can utilize the characteristic of them to inference several tasks, simultaneously. The results of experiments were demonstrated that the network could get a comparable performance to single-wavelength single-task. Compared to the multi-network, single network can save the cost of fabrication with lithography. We train the network on MNIST and MNIST-FASHION which are two different datasets to perform classification of 32*32 inputs with 10 classes. Our method achieves competitive results across both of them. In particular, on the complex task MNIST-FASION, our framework obtains an excellent accuracy improvement with 3.2%. On the meanwhile, MNSIT also have the improvement with 1.15%.
