One-core neuron deep learning for time series prediction

作     者：Hao Peng Pei Chen Na Yang Kazuyuki Aihara Rui Liu Luonan Chen Hao Peng;Pei Chen;Na Yang;Kazuyuki Aihara;Rui Liu;Luonan Chen

作者机构：School of Mathematics South China University of Technology School of Future TechnologySouth China University of Technology International Research Center for Neurointelligence The University of Tokyo Institutes for Advanced Study The University of Tokyo Key Laboratory of Systems Health Science of Zhejiang ProvinceSchool of Life ScienceHangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesChinese Academy of Sciences Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Guangdong Institute of Intelligence Science and Technology 

出 版 物：《National Science Review》 (国家科学评论(英文版))

年 卷 期：2025年第12卷第2期

页      面：315-328页

核心收录：

学科分类：12[管理学] 02[经济学] 07[理学] 08[工学] 070103[理学-概率论与数理统计] 0202[经济学-应用经济学] 020208[经济学-统计学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 0835[工学-软件工程] 0714[理学-统计学（可授理学、经济学学位）] 0811[工学-控制科学与工程] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China (12322119, T2341022, 62172164, 12271180,T2350003, T2341007, 31930022, 12426310 and 12131020) the Science and Technology Commission of Shanghai Municipality(23JS1401300) the Japan Science and Technology Agency Moonshot R&D (JPMJMS2021) the Japan Agency for Medical Research and Development (AMED)(JP23dm0307009) the Institute of AI and Beyond at The University of Tokyo,the International Research Center for Neurointelligence (WPI-IRCN) at the University of Tokyo Institutes for Advanced Study (UTIAS),the Japan Society for the Promotion of Science (JSPS) Grantsin-Aid for Scientific Research (KAKENHI)(JP20H05921) the Guangdong Basic and Applied Basic Research Foundation(2024A1515011797) the Fundamental Research Funds for the Central Universities (2023ZYGXZR077) 

主　　题：spatiotemporal information (STI) transformation one-core-neuron (OCN) small model deep learning time-series prediction large model 

摘      要：The enormous computational requirements and unsustainable resource consumption associated with massive parameters of large language models and large vision models have given rise to challenging ***, we propose an interpretable ‘small model’ framework characterized by only a single core-neuron, *** one-core-neuron system(OCNS), to significantly reduce the number of parameters while maintaining performance comparable to the existing ‘large models’ in time-series forecasting. With multiple delay feedback designed in this single neuron, our OCNS is able to convert one input feature vector/state into one-dimensional time-series/sequence, which is theoretically ensured to fully represent the states of the observed dynamical system. Leveraging the spatiotemporal information transformation, the OCNS shows excellent and robust performance in forecasting tasks, in particular for short-term high-dimensional systems. The results collectively demonstrate that the proposed OCNS with a single core neuron offers insights into constructing deep learning frameworks with a small model, presenting substantial potential as a new way for achieving efficient deep learning.