近日,清华大学的方璐及其研究团队取得一项新进展。经过不懈努力,他们开发出用于数十项任务终身学习的光子神经形态架构。相关研究成果已于2024年2月26日在国际知名学术期刊《光:科学与应用》上发表。
该研究团队创新性地开发了一种可重构的终身学习光神经网络(L2ONN),专门用于高度集成化的数十种任务机器智能。该网络融合了精心设计的算法与硬件协同设计理念。通过利用海量光子连接所固有的稀疏性和并行性,L2ONN能够自适应地激活相干光场中的稀疏光子神经元连接,从而学习每个单独的任务,并通过逐步扩大激活范围来逐步获得各种任务的专业知识。为了并行处理多任务光学特征,L2ONN采用了多光谱表示,通过分配不同的波长来区分不同的任务。经过对自由空间和片上架构的广泛评估,L2ONN首次成功地避免了光子计算中常见的灾难性遗忘问题。
它使用单一模型就具备了处理具有挑战性的数十种任务(如视觉分类、语音识别、医疗诊断等)的多功能技能。特别值得一提的是,L2ONN的效率比代表性电子人工神经网络高出一个数量级,容量比现有光神经网络大14倍,同时在每个单独的任务上都能保持竞争性能。这一创新性的光子神经形态架构为终身学习提供了新的方案,使终端/边缘人工智能系统能够以光速效率和前所未有的可扩展性运行。
据悉,可扩展、高容量和低功耗的计算架构是日益多样化和大规模机器学习任务的主要保证。传统的电子人工智能体采用传统的耗电处理器,面临着能量和缩放墙的问题,这阻碍了其可持续的性能改进和迭代的多任务学习。光子计算是光的另一种形式,已逐步应用于高效的神经形态系统。
附:英文原文
Title: Photonic neuromorphic architecture for tens-of-task lifelong learning
Author: Cheng, Yuan, Zhang, Jianing, Zhou, Tiankuang, Wang, Yuyan, Xu, Zhihao, Yuan, Xiaoyun, Fang, Lu
Issue&Volume: 2024-02-26
Abstract: Scalable, high-capacity, and low-power computing architecture is the primary assurance for increasingly manifold and large-scale machine learning tasks. Traditional electronic artificial agents by conventional power-hungry processors have faced the issues of energy and scaling walls, hindering them from the sustainable performance improvement and iterative multi-task learning. Referring to another modality of light, photonic computing has been progressively applied in high-efficient neuromorphic systems. Here, we innovate a reconfigurable lifelong-learning optical neural network (L2ONN), for highly-integrated tens-of-task machine intelligence with elaborated algorithm-hardware co-design. Benefiting from the inherent sparsity and parallelism in massive photonic connections, L2ONN learns each single task by adaptively activating sparse photonic neuron connections in the coherent light field, while incrementally acquiring expertise on various tasks by gradually enlarging the activation. The multi-task optical features are parallelly processed by multi-spectrum representations allocated with different wavelengths. Extensive evaluations on free-space and on-chip architectures confirm that for the first time, L2ONN avoided the catastrophic forgetting issue of photonic computing, owning versatile skills on challenging tens-of-tasks (vision classification, voice recognition, medical diagnosis, etc.) with a single model. Particularly, L2ONN achieves more than an order of magnitude higher efficiency than the representative electronic artificial neural networks, and 14× larger capacity than existing optical neural networks while maintaining competitive performance on each individual task. The proposed photonic neuromorphic architecture points out a new form of lifelong learning scheme, permitting terminal/edge AI systems with light-speed efficiency and unprecedented scalability.
DOI: 10.1038/s41377-024-01395-4
Source: https://www.nature.com/articles/s41377-024-01395-4
Light: Science & Applications:《光:科学与应用》,创刊于2012年。隶属于施普林格·自然出版集团,最新IF:19.4
官方网址:https://www.nature.com/lsa/
投稿链接:https://mts-lsa.nature.com/cgi-bin/main.plex