近日，美国加州理工学院的Alireza Marandi及其研究团队取得一项新进展。经过不懈努力，他们实现基于光子神经元胞自动机的深度学习。相关研究成果已于2024年10月8日在国际知名学术期刊《光：科学与应用》上发表。

为了克服这些限制，该研究团队提出光子神经元胞自动机（PNCA），并通过实验验证了其在具有稀疏连接性的光子深度学习中的应用。PNCA利用光子学的速度和互联性，以及元胞自动机通过局部相互作用实现的自组织特性，来实现稳健、可靠和高效的处理。

研究人员在时间复用光子网络中利用线性光干涉和参数非线性光学进行全光学计算，以实验方式执行自组织图像分类。他们使用仅3个可编程光子参数实现了图像的二元（两类）分类，并获得了高实验准确率，同时能够识别分布外数据。

所提出的PNCA方法可适应多种现有光子硬件，并通过最大化基于光的计算的优势同时缓解其实际挑战，为传统光子神经网络提供了一种有力的替代方案。这项研究结果展示了PNCA在推动光子深度学习方面的潜力，并为下一代光子计算机的发展指明了方向。

据悉，过去十年深度学习技术的迅猛发展，激发了对高效、可扩展硬件的迫切需求。光子学利用光的独特性质，提供了一种颇具前景的解决方案。然而，传统神经网络架构通常需要密集的可编程连接，这对光子实现构成了若干实际挑战。

附：英文原文

Title: Deep learning with photonic neural cellular automata

Author: Li, Gordon H. Y., Leefmans, Christian R., Williams, James, Gray, Robert M., Parto, Midya, Marandi, Alireza

Issue&Volume: 2024-10-08

Abstract: Rapid advancements in deep learning over the past decade have fueled an insatiable demand for efficient and scalable hardware. Photonics offers a promising solution by leveraging the unique properties of light. However, conventional neural network architectures, which typically require dense programmable connections, pose several practical challenges for photonic realizations. To overcome these limitations, we propose and experimentally demonstrate Photonic Neural Cellular Automata (PNCA) for photonic deep learning with sparse connectivity. PNCA harnesses the speed and interconnectivity of photonics, as well as the self-organizing nature of cellular automata through local interactions to achieve robust, reliable, and efficient processing. We utilize linear light interference and parametric nonlinear optics for all-optical computations in a time-multiplexed photonic network to experimentally perform self-organized image classification. We demonstrate binary (two-class) classification of images using as few as 3 programmable photonic parameters, achieving high experimental accuracy with the ability to also recognize out-of-distribution data. The proposed PNCA approach can be adapted to a wide range of existing photonic hardware and provides a compelling alternative to conventional photonic neural networks by maximizing the advantages of light-based computing whilst mitigating their practical challenges. Our results showcase the potential of PNCA in advancing photonic deep learning and highlights a path for next-generation photonic computers.

DOI: 10.1038/s41377-024-01651-7

Source: https://www.nature.com/articles/s41377-024-01651-7