Duan Zhengyang, Chen Hang, Lin Xing
Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.
Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China.
Nanophotonics. 2023 Jan 16;12(5):893-903. doi: 10.1515/nanoph-2022-0615. eCollection 2023 Mar.
Photonic neural networks are brain-inspired information processing technology using photons instead of electrons to perform artificial intelligence (AI) tasks. However, existing architectures are designed for a single task but fail to multiplex different tasks in parallel within a single monolithic system due to the task competition that deteriorates the model performance. This paper proposes a novel optical multitask learning system by designing multiwavelength diffractive deep neural networks (DNNs) with the joint optimization method. By encoding multitask inputs into multiwavelength channels, the system can increase the computing throughput and significantly alleviate the competition to perform multiple tasks in parallel with high accuracy. We design the two-task and four-task DNNs with two and four spectral channels, respectively, for classifying different inputs from MNIST, FMNIST, KMNIST, and EMNIST databases. The numerical evaluations demonstrate that, under the same network size, multiwavelength DNNs achieve significantly higher classification accuracies for multitask learning than single-wavelength DNNs. Furthermore, by increasing the network size, the multiwavelength DNNs for simultaneously performing multiple tasks achieve comparable classification accuracies with respect to the individual training of multiple single-wavelength DNNs to perform tasks separately. Our work paves the way for developing the wavelength-division multiplexing technology to achieve high-throughput neuromorphic photonic computing and more general AI systems to perform multiple tasks in parallel.
光子神经网络是一种受大脑启发的信息处理技术，它使用光子而非电子来执行人工智能（AI）任务。然而，现有的架构是为单一任务设计的，由于任务竞争会降低模型性能，因此无法在单个整体系统中并行复用不同任务。本文通过采用联合优化方法设计多波长衍射深度神经网络（DNN），提出了一种新颖的光学多任务学习系统。通过将多任务输入编码到多波长通道中，该系统可以提高计算吞吐量，并显著缓解并行执行多个任务时的竞争，从而高精度地完成任务。我们分别设计了具有两个和四个光谱通道的双任务和四任务DNN，用于对来自MNIST、FMNIST、KMNIST和EMNIST数据库的不同输入进行分类。数值评估表明，在相同网络规模下，多波长DNN在多任务学习中比单波长DNN具有显著更高的分类准确率。此外，通过增加网络规模，用于同时执行多个任务的多波长DNN在分类准确率方面与分别训练多个单波长DNN来单独执行任务相当。我们的工作为开发波分复用技术以实现高通量神经形态光子计算以及更通用的并行执行多个任务的AI系统铺平了道路。
