Inferring network structures from available data has attracted much interest in network science;however,in many realistic networks,only some of the nodes are perceptible while others are hidden,making it a challenging...Inferring network structures from available data has attracted much interest in network science;however,in many realistic networks,only some of the nodes are perceptible while others are hidden,making it a challenging task.In this work,we develop a method for reconstructing the network with hidden nodes and links,taking account of fast-varying noise and time-delay interactions.By calculating the correlations of available data with different derivative orders for multiple pairs of accessible nodes,analyzing and integrating the relationships between different correlations,and defining diverse hidden-node-related reconstruction motifs,we can effectively identify the hidden nodes and hidden links in the network.展开更多
Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data ana...Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data analysis.This paper presents a model based on these nanowire networks,with an improved conductance variation profile.We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses.The nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction analysis.Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction accuracy.Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.11835003)supported by the National Natural Science Foundation of China(Grant Nos.12375033,12235007,and 11975131)+7 种基金the Natural Science Foundation of Zhejiang(Grant No.LY23A050002)the K.C.Wong Magna Fund at Ningbo Universitysupported by the National Natural Science Foundation of China(Grant No.T2122016)the National Science and Technology Innovation 2030 Major Program(Grant Nos.2021ZD0203700,and 2021ZD0203705)the Fundamental Research Funds for the Central Universities(Grant No.2022CDJKYJH034)supported by the National Institutes of Health(Grant Nos.R01 HL134709,R01 HL139829,R01 HL157116,and P01 HL164311)supported by the National Natural Science Foundation of China(Grant No.11905291)CAS Project for Young Scientists in Basic Research(Grant No.YSBR-041)。
文摘Inferring network structures from available data has attracted much interest in network science;however,in many realistic networks,only some of the nodes are perceptible while others are hidden,making it a challenging task.In this work,we develop a method for reconstructing the network with hidden nodes and links,taking account of fast-varying noise and time-delay interactions.By calculating the correlations of available data with different derivative orders for multiple pairs of accessible nodes,analyzing and integrating the relationships between different correlations,and defining diverse hidden-node-related reconstruction motifs,we can effectively identify the hidden nodes and hidden links in the network.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. U20A20227,62076208, and 62076207)Chongqing Talent Plan “Contract System” Project (Grant No. CQYC20210302257)+3 种基金National Key Laboratory of Smart Vehicle Safety Technology Open Fund Project (Grant No. IVSTSKL-202309)the Chongqing Technology Innovation and Application Development Special Major Project (Grant No. CSTB2023TIAD-STX0020)College of Artificial Intelligence, Southwest UniversityState Key Laboratory of Intelligent Vehicle Safety Technology
文摘Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data analysis.This paper presents a model based on these nanowire networks,with an improved conductance variation profile.We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses.The nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction analysis.Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction accuracy.Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.
