摘要
光子储备池因其反馈连接的拓扑结构,在时间序列任务中展现出巨大潜力,主要形式包括延时型、波导型、空间光型和空腔型储备池。其中,波导型集成光子储备池具有并行输入和高集成度的特点,在时间序列二进制任务中表现突出。然而,针对更复杂的模拟数值预测任务,传统方法下的单个集成光子储备池因物理节点数量有限,导致计算性能不足。为解决这一问题,提出了一种32节点梅花形光子储备池芯片,外围节点作为输入输出节点,各输入节点通过强度调制引入非线性效应,接收不同的调制信号,各输出节点基于历史数据,采用向量自回归算法进行训练,从而实现更高效且精确的时间序列预测任务。研究结果表明:通过优化输入策略、芯片设计和训练算法,32节点集成光子储备池相较于传统延时型光子储备池,在预测任务中的RMSE和NMSE指标分别提升了两个和一个数量级,使波导型集成光子储备池在时间序列预测任务中成为有力竞争方法。
Objective Photonic reservoirs have emerged as a promising complementary solution for computing hardware platforms,offering significant advantages in addressing time-dependent tasks and thus attracting substantial attention.Waveguide-based photonic reservoirs,in particular,have shown exceptional performance in time-series applications,such as communication and bit-level processing tasks.For more complex analog prediction tasks,studies have validated the efficacy of larger reservoirs,comprising up to 128 nodes,for the Santa Fe chaotic laser prediction challenge.However,this approach suffers from the limitation of requiring a large physical footprint.To overcome this constraint,the present study refines algorithmic techniques and input strategies,enabling accurate predictions using a more compact integrated photonic reservoir.Methods First,to process the high-dimensional sampled data from the reservoir chip,the data processing algorithm was transitioned from linear regression to vector autoregression(VAR).VAR allows the incorporation of additional historical sample data as feature inputs in linear combinations,thereby alleviating computational limitations imposed by the restricted number of output nodes.Building on this improvement,a 32-node plumshaped integrated photonic reservoir is proposed for predictive tasks.Finally,a multiple-dissimilar-input strategy is introduced to enhance data diversity at the input layer,further reducing computational errors in time-series prediction tasks.Results and Discussions The results of research demonstrate that compact integrated reservoir computing,when combined with the VAR algorithm,achieves highly accurate prediction results.The prediction errors remain within the same order of magnitude as those in delay-based reservoirs,positioning the small integrated photonic reservoir as a strong competitor in this category.Building on this foundation,our investigation extended to the input strategy,demonstrating the effectiveness of a multiple-dissimilar-input approach.Compared to trad
作者
裴丽
丁保钦
白冰
白博文
隋娟
王建帅
宁提纲
PEI Li;DING Baoqin;BAI Bing;BAI Bowen;SUI Juan;WANG Jianshuai;NING Tigang(Key Laboratory of All-Optical Networks and Modern Communication Networks of Ministry of Education,Institute of Lightwave Technology,Beijing Jiaotong University,Beijing 100044,China;Photoncounts(Beijing)Technology Company Ltd.,Beijing 100081,China;State Key Laboratory of Advanced Optical Communications System and Networks,School of Electronics,Peking University,Beijing 100871,China)
出处
《红外与激光工程》
EI
CSCD
北大核心
2024年第10期30-39,共10页
Infrared and Laser Engineering
基金
国家自然科学基金项目(62235003)
北京交通大学自然科学人才基金项目(2023XKRC040)。
关键词
光子储备池
时间序列预测
集成光学
向量自回归
photonic reservoir computing
time-series prediction
integrated photonic circuits
vector autoregressive
