[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8,"_9":10},"actionData","errors","root",{"_353":354},"routes/_layout",{"_11":264},"routes/entity.$type.$id",{"_11":12,"_13":14,"_15":16,"_17":18,"_19":20,"_21":22,"_23":24,"_25":26,"_27":28},"dehydratedState",{"_58":59,"_60":61},"type","technology","id","tech_oa_T11347","section","children","entity",{"_15":16,"_29":30,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":38,"_39":-5,"_40":41,"_42":43,"_44":45,"_46":47,"_48":49,"_50":-5,"_51":52,"_53":-5,"_54":-5,"_55":-5,"_56":30,"_57":-5},"canonical","https://www.hugmap.com/entity/technology/tech_oa_T11347/children","siteBaseUrl","https://www.hugmap.com","sectionCount",0,"jsonLd","{\"@context\":\"https://schema.org\",\"@graph\":[{\"name\":\"Neural Networks Stability and Synchronization\",\"url\":\"https://www.hugmap.com/entity/technology/tech_oa_T11347/children\",\"@type\":\"DefinedTerm\",\"inDefinedTermSet\":\"HugMap Technology Glossary\"},{\"@type\":\"CollectionPage\",\"name\":\"Neural Networks Stability and Synchronization 衍生技术\",\"description\":\"Neural Networks Stability and Synchronization 在 HugMap 中的衍生技术，含结构化关联信息与详情链接。\",\"url\":\"https://www.hugmap.com/entity/technology/tech_oa_T11347/children\",\"inLanguage\":\"zh-CN\"},{\"@type\":\"BreadcrumbList\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"首页\",\"item\":\"https://www.hugmap.com/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"技术\",\"item\":\"https://www.hugmap.com/search?type=technology\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Neural Networks Stability and Synchronization\",\"item\":\"https://www.hugmap.com/entity/technology/tech_oa_T11347\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"衍生技术\",\"item\":\"https://www.hugmap.com/entity/technology/tech_oa_T11347/children\"}]}]}","name","Neural Networks Stability and Synchronization","nameZh","aliases","description","descriptionZh","status","active","externalIds","{\"taxonomy_id\":\"tax_rd_T11347\"}","properties","source","openalex_topics","createdAt","2026-05-17T09:00:39.268657985","updatedAt","2026-05-17T09:00:39.268659823","techType","architecture","domain","Physical Sciences","proposedYear","maturityLevel","growing","wikipediaUrl","paperCount","patentCount","displayName","displayDescription","mutations",[],"queries",[62],{"_63":64,"_65":66,"_67":68,"_69":70},"dehydratedAt",1780525523249,"state",{"_72":73,"_74":75,"_76":64,"_77":-5,"_78":26,"_79":26,"_80":26,"_81":-5,"_82":-5,"_83":84,"_35":85,"_86":87},"queryKey",[71,19,14,16],"queryHash","[\"portal\",\"entity\",\"technology\",\"tech_oa_T11347\"]","portal","data",{"_19":20,"_88":89,"_90":91,"_92":93,"_94":95,"_96":97,"_98":99,"_100":101,"_18":102},"dataUpdateCount",1,"dataUpdatedAt","error","errorUpdateCount","errorUpdatedAt","fetchFailureCount","fetchFailureReason","fetchMeta","isInvalidated",false,"success","fetchStatus","idle","entityType","Technology","taxonomies",[],"papers",[103,104,105,106,107,108,109,110,111,112],"events",[],"patents",[],"articles",[],"products",[],[],{"_15":249,"_29":250,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":251,"_39":-5,"_40":116,"_42":252,"_44":253,"_119":254,"_121":255,"_122":256,"_124":250,"_125":257,"_127":258,"_129":259,"_131":260,"_133":261,"_135":-5,"_136":262,"_138":263,"_139":84,"_56":250,"_57":-5},{"_15":238,"_29":239,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":240,"_39":-5,"_40":116,"_42":241,"_44":242,"_119":243,"_121":-5,"_122":244,"_124":239,"_125":245,"_127":219,"_129":150,"_131":220,"_133":246,"_135":-5,"_136":247,"_138":-5,"_139":84,"_56":239,"_57":-5},{"_15":225,"_29":226,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":227,"_39":-5,"_40":116,"_42":228,"_44":229,"_119":230,"_121":-5,"_122":231,"_124":226,"_125":232,"_127":233,"_129":234,"_131":235,"_133":236,"_135":-5,"_136":237,"_138":-5,"_139":84,"_56":226,"_57":-5},{"_15":211,"_29":212,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":213,"_39":-5,"_40":116,"_42":214,"_44":215,"_119":216,"_121":-5,"_122":217,"_124":212,"_125":218,"_127":219,"_129":150,"_131":220,"_133":221,"_135":-5,"_136":222,"_138":-5,"_139":84,"_56":212,"_57":-5},{"_15":199,"_29":200,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":201,"_39":-5,"_40":116,"_42":202,"_44":203,"_119":204,"_121":-5,"_122":205,"_124":200,"_125":206,"_127":207,"_129":208,"_131":-5,"_133":209,"_135":-5,"_136":210,"_138":-5,"_139":84,"_56":200,"_57":-5},{"_15":184,"_29":185,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":186,"_39":-5,"_40":116,"_42":187,"_44":188,"_119":189,"_121":-5,"_122":190,"_124":185,"_125":191,"_127":192,"_129":193,"_131":194,"_133":195,"_135":-5,"_136":196,"_138":-5,"_139":84,"_56":185,"_57":-5},{"_15":171,"_29":172,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":173,"_39":-5,"_40":116,"_42":174,"_44":175,"_119":176,"_121":-5,"_122":177,"_124":172,"_125":-5,"_127":178,"_129":179,"_131":151,"_133":180,"_135":-5,"_136":181,"_138":182,"_139":84,"_56":172,"_57":-5},{"_15":156,"_29":157,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":158,"_39":-5,"_40":116,"_42":159,"_44":160,"_119":161,"_121":-5,"_122":162,"_124":157,"_125":163,"_127":164,"_129":165,"_131":166,"_133":167,"_135":-5,"_136":168,"_138":-5,"_139":84,"_56":157,"_57":-5},{"_15":142,"_29":143,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":144,"_39":-5,"_40":116,"_42":145,"_44":146,"_119":147,"_121":-5,"_122":148,"_124":143,"_125":-5,"_127":149,"_129":150,"_131":151,"_133":152,"_135":-5,"_136":153,"_138":-5,"_139":84,"_56":143,"_57":-5},{"_15":113,"_29":114,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":115,"_39":-5,"_40":116,"_42":117,"_44":118,"_119":120,"_121":-5,"_122":123,"_124":114,"_125":126,"_127":128,"_129":130,"_131":132,"_133":134,"_135":-5,"_136":137,"_138":-5,"_139":84,"_56":114,"_57":-5},"paper_W1986024064","Adaptive Neural Network Control of an Uncertain Robot With Full-State Constraints","{\"openalex\":\"W1986024064\",\"doi\":\"10.1109/tcyb.2015.2411285\"}","openalex","2026-05-14T09:14:43.200581459","2026-05-21T12:24:08.183654924","doi","10.1109/tcyb.2015.2411285","arxivId","openalexId","W1986024064","title","abstractText","This paper studies the tracking control problem for an uncertain n -link robot with full-state constraints. The rigid robotic manipulator is described as a multiinput and multioutput system. Adaptive neural network (NN) control for the robotic system with full-state constraints is designed. In the control design, the adaptive NNs are adopted to handle system uncertainties and disturbances. The Moore-Penrose inverse term is employed in order to prevent the violation of the full-state constraints. A barrier Lyapunov function is used to guarantee the uniform ultimate boundedness of the closed-loop system. The control performance of the closed-loop system is guaranteed by appropriately choosing the design parameters. Simulation studies are performed to illustrate the effectiveness of the proposed control.","publishedDate","2015-04-03","publishedYear",2015,"venue","IEEE Transactions on Cybernetics","citationCount",1255,"authors","keywords",[140,141,30],"pdfUrl","topVenue","Adaptive Control of Nonlinear Systems","Adaptive Dynamic Programming Control","paper_W1996773027","Nonlinear neural networks: Principles, mechanisms, and architectures","{\"openalex\":\"W1996773027\",\"doi\":\"10.1016/0893-6080(88)90021-4\"}","2026-05-14T06:15:12.314238342","2026-05-21T08:35:31.215880681","10.1016/0893-6080(88)90021-4","W1996773027","1988-01-01",1988,"Neural Networks",1631,[154,155,30],"Neural dynamics and brain function","Neural Networks and Applications","paper_W2095509930","A Delay System Method for Designing Event-Triggered Controllers of Networked Control Systems","{\"openalex\":\"W2095509930\",\"doi\":\"10.1109/tac.2012.2206694\"}","2026-05-14T06:10:17.363743419","2026-05-21T08:23:08.294060894","10.1109/tac.2012.2206694","W2095509930","This note is concerned with event-triggered H _∞ controller design for networked control systems. A novel event-triggering scheme is proposed, which has some advantages over some existing schemes. A delay system model for the analysis is firstly constructed by investigating the effect of the network transmission delay. Then, based on this model, criteria for stability with an H _∞ norm bound and criteria for co-designing both the feedback gain and the trigger parameters are derived. These criteria are formulated in terms of linear matrix inequalities. Simulation results have shown that the proposed event-triggering scheme is superior to some existing event-triggering schemes in the literature.","2012-06-29",2012,"IEEE Transactions on Automatic Control",1655,[169,30,170],"Stability and Control of Uncertain Systems","Matrix Theory and Algorithms","paper_W2012611887","Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system","{\"openalex\":\"W2012611887\",\"doi\":\"10.1016/0893-6080(91)90056-b\"}","2026-05-14T06:07:52.471004027","2026-05-21T08:19:16.235397086","10.1016/0893-6080(91)90056-b","W2012611887","1991-01-01",1991,1671,[155,30,183],"https://open.bu.edu/bitstreams/7bb6fedf-5b64-4f2a-ade6-90b691f58b3d/download","Advanced Memory and Neural Computing","paper_W2158054309","A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks","{\"openalex\":\"W2158054309\",\"doi\":\"10.1109/tnn.2006.880583\"}","2026-05-14T04:41:12.218898377","2026-05-21T07:00:30.183799712","10.1109/tnn.2006.880583","W2158054309","In this paper, we develop an online sequential learning algorithm for single hidden layer feedforward networks (SLFNs) with additive or radial basis function (RBF) hidden nodes in a unified framework. The algorithm is referred to as online sequential extreme learning machine (OS-ELM) and can learn data one-by-one or chunk-by-chunk (a block of data) with fixed or varying chunk size. The activation functions for additive nodes in OS-ELM can be any bounded nonconstant piecewise continuous functions and the activation functions for RBF nodes can be any integrable piecewise continuous functions. In OS-ELM, the parameters of hidden nodes (the input weights and biases of additive nodes or the centers and impact factors of RBF nodes) are randomly selected and the output weights are analytically determined based on the sequentially arriving data. The algorithm uses the ideas of ELM of Huang et al. developed for batch learning which has been shown to be extremely fast with generalization performance better than other batch training methods. Apart from selecting the number of hidden nodes, no other control parameters have to be manually chosen. Detailed performance comparison of OS-ELM is done with other popular sequential learning algorithms on benchmark problems drawn from the regression, classification and time series prediction areas. The results show that the OS-ELM is faster than the other sequential algorithms and produces better generalization performance.","2006-11-01",2006,"IEEE Transactions on Neural Networks",1965,[197,198,30],"Machine Learning and ELM","Face and Expression Recognition","paper_W2039708501","Theory of the backpropagation neural network","{\"openalex\":\"W2039708501\",\"doi\":\"10.1109/ijcnn.1989.118638\"}","2026-05-14T04:02:11.19187141","2026-05-21T06:01:36.24601243","10.1109/ijcnn.1989.118638","W2039708501","The author presents a survey of the basic theory of the backpropagation neural network architecture covering architectural design, performance measurement, function approximation capability, and learning. The survey includes previously known material, as well as some new results, namely, a formulation of the backpropagation neural network architecture to make it a valid neural network (past formulations violated the locality of processing restriction) and a proof that the backpropagation mean-squared-error function exists and is differentiable. Also included is a theorem showing that any L/sub 2/ function from (0, 1)/sup n/ to R/sup m/ can be implemented to any desired degree of accuracy with a three-layer backpropagation neural network. The author presents a speculative neurophysiological model illustrating how the backpropagation neural network architecture might plausibly be implemented in the mammalian brain for corticocortical learning between nearby regions of the cerebral cortex.< >","1989-01-01",1989,2233,[155,183,30],"paper_W2056717940","Cellular neural networks: applications","{\"openalex\":\"W2056717940\",\"doi\":\"10.1109/31.7601\"}","2026-05-14T03:51:24.246316059","2026-05-21T05:42:45.181536434","10.1109/31.7601","W2056717940","The theory of a novel class of information-processing systems, called cellular neural networks, which are capable of high-speed parallel signal processing, was presented in a previous paper (see ibid., vol.35, no.10, p.1257-72, 1988). A dynamic route approach for analyzing the local dynamics of this class of neural circuits is used to steer the system trajectories into various stable equilibrium configurations which map onto binary patterns to be recognized. Some applications of cellular neural networks to such areas as image processing and pattern recognition are demonstrated, albeit with only a crude circuit. In particular, examples of cellular neural networks which can be designed to recognize the key features of Chinese characters are presented.< >","1988-10-01","IEEE Transactions on Circuits and Systems",2377,[30,223,224],"Cellular Automata and Applications","Nonlinear Dynamics and Pattern Formation","paper_W2062210787","Absolute stability of global pattern formation and parallel memory storage by competitive neural networks","{\"openalex\":\"W2062210787\",\"doi\":\"10.1109/tsmc.1983.6313075\"}","2026-05-14T03:25:11.339075672","2026-05-21T05:21:14.289847222","10.1109/tsmc.1983.6313075","W2062210787","Systems that are competitive and possess symmetric interactions admit a global Lyapunov function. However, a global Lyapunov function whose equilibrium set can be effectively analyzed has not yet been discovered. It remains an open question whether the Lyapunov function approach, which requires a study of equilibrium points, or an alternative global approach, such as the Lyapunov functional approach, which sidesteps a direct study of equilibrium points will ultimately handle all of the physically important cases.","1983-09-01",1983,"IEEE Transactions on Systems Man and Cybernetics",2542,[155,154,30],"paper_W2160121923","Cellular neural networks: theory","{\"openalex\":\"W2160121923\",\"doi\":\"10.1109/31.7600\"}","2026-05-14T01:35:39.410618334","2026-05-21T03:16:36.212270589","10.1109/31.7600","W2160121923","A novel class of information-processing systems called cellular neural networks is proposed. Like neural networks, they are large-scale nonlinear analog circuits that process signals in real time. Like cellular automata, they consist of a massive aggregate of regularly spaced circuit clones, called cells, which communicate with each other directly only through their nearest neighbors. Each cell is made of a linear capacitor, a nonlinear voltage-controlled current source, and a few resistive linear circuit elements. Cellular neural networks share the best features of both worlds: their continuous-time feature allows real-time signal processing, and their local interconnection feature makes them particularly adapted for VLSI implementation. Cellular neural networks are uniquely suited for high-speed parallel signal processing.< >",4767,[223,30,248],"Quantum-Dot Cellular Automata","paper_W2060464767","Efficient Behavior of Small-World Networks","{\"arxiv\":\"cond-mat/0101396\",\"openalex\":\"W2060464767\",\"doi\":\"10.1103/physrevlett.87.198701\"}","2026-05-14T01:25:56.298662928","2026-05-21T03:06:50.201435509","10.1103/physrevlett.87.198701","cond-mat/0101396","W2060464767","We introduce the concept of efficiency of a network as a measure of how efficiently it exchanges information. By using this simple measure, small-world networks are seen as systems that are both globally and locally efficient. This gives a clear physical meaning to the concept of \"small world,\" and also a precise quantitative analysis of both weighted and unweighted networks. We study neural networks and man-made communication and transportation systems and we show that the underlying general principle of their construction is in fact a small-world principle of high efficiency.","2001-10-17",2001,"Physical Review Letters",5109,[155,154,30],"https://arxiv.org/pdf/cond-mat/0101396",{"_58":265,"_60":266},[],[267],{"_63":268,"_65":269,"_67":270,"_69":271},1780525522153,{"_72":273,"_74":75,"_76":268,"_77":-5,"_78":26,"_79":26,"_80":26,"_81":-5,"_82":-5,"_83":84,"_35":85,"_86":87},[71,272],"[\"portal\",\"industries\"]","industries",[274,275,276,277,278,279,280,281,282,283,284,285],{"_15":346,"_29":347,"_31":-5,"_32":348,"_33":349,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":350,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":347,"_57":349},{"_15":342,"_29":343,"_31":-5,"_32":-5,"_33":344,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":345,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":343,"_57":344},{"_15":336,"_29":337,"_31":-5,"_32":338,"_33":339,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":340,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":337,"_57":339},{"_15":332,"_29":333,"_31":-5,"_32":-5,"_33":334,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":335,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":333,"_57":334},{"_15":328,"_29":329,"_31":-5,"_32":-5,"_33":330,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":331,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":329,"_57":330},{"_15":322,"_29":323,"_31":-5,"_32":324,"_33":325,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":326,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":323,"_57":325},{"_15":317,"_29":318,"_31":-5,"_32":-5,"_33":319,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":320,"_298":26,"_299":321,"_300":26,"_18":-5,"_56":318,"_57":319},{"_15":313,"_29":314,"_31":-5,"_32":-5,"_33":315,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":316,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":314,"_57":315},{"_15":309,"_29":310,"_31":-5,"_32":-5,"_33":311,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":312,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":310,"_57":311},{"_15":305,"_29":306,"_31":-5,"_32":-5,"_33":307,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":308,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":306,"_57":307},{"_15":301,"_29":302,"_31":-5,"_32":-5,"_33":303,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":304,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":302,"_57":303},{"_15":286,"_29":287,"_31":-5,"_32":-5,"_33":288,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":289,"_42":-5,"_44":-5,"_290":291,"_292":-5,"_293":75,"_294":295,"_296":297,"_298":26,"_299":84,"_300":26,"_18":-5,"_56":287,"_57":288},"tax_ind_smartphone","智能手机","Smartphone","manual","taxonomyType","INDUSTRY","code","level","parentId","tax_ind_root","path","科技行业/智能手机","sortOrder","isLeaf","entityCount","tax_ind_robot","机器人","Robotics","科技行业/机器人","tax_ind_wearable","智能穿戴","Smart Wearables","科技行业/智能穿戴","tax_ind_energy","新能源与智能制造","New Energy & Smart Manufacturing","科技行业/新能源与智能制造","tax_ind_biotech","生物科技","Biotech","科技行业/生物科技","tax_ind_quantum","量子计算","Quantum Computing","科技行业/量子计算",true,"tax_ind_blockchain","区块链",[327],"Blockchain","科技行业/区块链","Web3","tax_ind_enterprise","企业软件","Enterprise Software","科技行业/企业软件","tax_ind_security","网络安全","Cybersecurity","科技行业/网络安全","tax_ind_semi","半导体",[341],"Semiconductor","科技行业/半导体","芯片","tax_ind_cloud","云计算","Cloud Computing","科技行业/云计算","tax_ind_ai","人工智能",[351,352],"Artificial Intelligence","科技行业/人工智能","AI","AI 技术","env",{"_355":24},"SITE_BASE_URL"]

Neural Networks Stability and Synchronization 技术

Neural Networks Stability and Synchronization · 衍生技术