Recently, there has been tremendous research studies 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 phases at different diffractive points (Chen and Zhu, 2019 and Mo et al., 2018). In this study, it proposed a multiwave 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 multinetwork, 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%. In the meanwhile, MNSIT also has the improvement with 1.15%.

中文翻译：

---

多波光衍射网络的多任务学习

近来，在光学神经网络中进行了大量的研究，可以通过光学特性完成相对复杂的计算，并且耗散性比电气网络少得多。现有的基于光学电路的神经网络是由一个光栅平台构成的，该平台在不同的衍射点具有不同的衍射相（Chen和Zhu，2019年; Mo等人，2018年）。在这项研究中，它提出了一个约10 ⁶的多波深衍射网络。突触，很容易使神经形态网络的硬件实现。在光学架构中，它可以利用光学衍射特性和不同的波长来执行不同的任务。不同的波长和不同的任务输入彼此独立。此外，我们可以利用它们的特性来同时推断多个任务。实验结果表明，该网络可以获得与单波长单任务相当的性能。与多网络相比，单个网络可以节省使用光刻的制造成本。我们在MNIST和MNIST-FASHION上训练网络，这是两个不同的数据集，可以对10个类别的32 * 32输入进行分类。我们的方法在两者上均取得了竞争性结果。尤其是，在复杂任务MNIST_FASION上，我们的框架的准确性提高了3.2％。同时，MNSIT也有1.15％的改善。