Filters








151 Hits in 7.0 sec

Hopfield Neural Networks for Parametric Identification of Dynamical Systems

Miguel Atencia, Gonzalo Joya, Francisco Sandoval
2005 Neural Processing Letters  
function also varies with time.  ...  In this work, a novel method, based upon Hopfield neural networks, is proposed for parameter estimation, in the context of system identification.  ...  The careful reading and useful suggestions of the reviewers are gratefully acknowledged.  ... 
doi:10.1007/s11063-004-3424-3 fatcat:qhosfuhohvespd26nvdfrbf6la

Multi-Robot Energy-Efficient Coverage Control with Hopfield Networks

Mert TURANLI, Hakan TEMELTAS
2020 Studies in Informatics and Control  
The control problem of the multi-robots with different actuation capabilities has caught the attention of the robotics researchers over the last years.  ...  The algorithm proposed in the paper not only makes use of the energy-efficient coverage optimal control scheme but also utilizes Hopfield Neural Networks (HNN) in order to perform collaboration among the  ...  In the paper (Atencia, Joya & Sandoval, 2004) , an online identification method for non-linear systems with Hopfield networks is proposed.  ... 
doi:10.24846/v29i2y202004 fatcat:7w7h6mb24zckpl3xecmknyzho4

Neural networks: Algorithms and applications

Derong Liu, Huaguang Zhang, Sanqing Hu
2008 Neurocomputing  
Wang, Jian, and Guo discuss the existence and uniqueness and the global exponential stability of the equilibrium point for Cohen-Grossberg type BAM neural networks with time-varying delays and continuously  ...  Xu, Wang, and Liao analyze the stability of high-order Hopfield type neural networks with uncertainties which are assumed to be bounded.  ... 
doi:10.1016/j.neucom.2007.09.001 fatcat:bpuxqwm74vfm3m33j4wbwetnmu

2009 Index IEEE Transactions on Automatic Control Vol. 54

2009 IEEE Transactions on Automatic Control  
., +, TAC Sept. 2009 2114-2125 Hopfield neural nets Performance Analysis of Gradient Neural Network Exploited for Online Time-Varying Matrix Inversion.  ...  ., +, TAC May 2009 1019-1024 Stability of Networked Control Systems With Uncertain Time-Varying Delays. Cloosterman, M. B.  ...  State Convergence of Passive Nonlinear Systems With an L Input.  ... 
doi:10.1109/tac.2009.2037798 fatcat:4ilhkzss6jc63ersjzi47hiwgu

Neurodynamics in the Sensorimotor Loop: Representing Behavior Relevant External Situations

Frank Pasemann
2017 Frontiers in Neurorobotics  
This is carefully done by addressing the problem in three steps, using the time-discrete dynamics of standard neural networks and a fiber space representation for better clearness.  ...  a class of sensor inputs all generating the "same type" of dynamic behavior, and a dynamical form comprises the corresponding class of parametrized dynamical systems.  ...  * ∈ Q a set of dynamical systems (A, f ρ ) which are parametrically stable with respect to ρ * ∈ Q.  ... 
doi:10.3389/fnbot.2017.00005 pmid:28217092 pmcid:PMC5289985 fatcat:2hcax5fwojgqfgadgb4uqrz6vu

A Novel Recurrent Adaptive Backstepping Optimal Control Strategy for a Single Inverted Pendulum System [article]

Mohammad Sarbaz
2021 arXiv   pre-print
Here, first of all, the backstepping control laws are investigated based on the nonlinear dynamic model of the system.  ...  At last, the stability analysis of the system is studied using Lyapunov function.  ...  This problem is similar to the concept of training of the Hopfield network.  ... 
arXiv:2110.09846v1 fatcat:lvulahp355cx7a23gjimodepey

Neural Networks and Their Application to Power Engineering [chapter]

Mohamed A. El-Sharkawi, Robert J. Marks, Siri Weerasooriya
1991 Control and Dynamic Systems  
This is a key idea that could be applied to training NN' s for problems with time varying power system topologies.  ...  LOAD FORECASTING Forecasting electrical load in a power system with lead-times varying from hours to days, has obvious economic as well as other advantages.  ... 
doi:10.1016/b978-0-12-012741-2.50012-9 fatcat:3qhnsfbe6bhxnihk6tmelo5jbi

Evolution of adaptive learning for nonlinear dynamic systems: a systematic survey

Mouhcine Harib, Hicham Chaoui, Suruz Miah
2022 Intelligence & Robotics  
based on the experience they have with the system while training or possibly enhance it in real-time as well.  ...  In the 1990s, the field of Artificial Neural Networks was hugely investigated in general, and for control of dynamical systems in particular.  ...  problem for discrete-time systems with control constraints NNs: Neural Networks.  ... 
doi:10.20517/ir.2021.19 fatcat:xwp7dc3j6rdrraumuc5xigzici

IEEE Robotics & Automation Society

2012 IEEE robotics & automation magazine  
INESC-ID The problem of time-varying parameter identification is considered on a class of nonlinear hybrid systems.  ...  At each time instant, this network produces an estimate of the beam parameters and this estimate is the same for all beam points. In turn, the second method combines several Hopfield neural networks.  ... 
doi:10.1109/mra.2012.2230568 fatcat:33actbknxrel3jnag2kx7cncem

IEEE Robotics & Automation Society

2011 IEEE robotics & automation magazine  
INESC-ID The problem of time-varying parameter identification is considered on a class of nonlinear hybrid systems.  ...  At each time instant, this network produces an estimate of the beam parameters and this estimate is the same for all beam points. In turn, the second method combines several Hopfield neural networks.  ... 
doi:10.1109/mra.2011.941112 fatcat:owvu2behc5hulpcae2dp5myigm

[IEEE Robotics & Automation Society]

2012 IEEE robotics & automation magazine  
INESC-ID The problem of time-varying parameter identification is considered on a class of nonlinear hybrid systems.  ...  At each time instant, this network produces an estimate of the beam parameters and this estimate is the same for all beam points. In turn, the second method combines several Hopfield neural networks.  ... 
doi:10.1109/mra.2012.2229854 fatcat:rjrxtwk4jbcgjpvjdad6mougsq

IEEE Robotics & Automation Society

2011 IEEE robotics & automation magazine  
INESC-ID The problem of time-varying parameter identification is considered on a class of nonlinear hybrid systems.  ...  At each time instant, this network produces an estimate of the beam parameters and this estimate is the same for all beam points. In turn, the second method combines several Hopfield neural networks.  ... 
doi:10.1109/mra.2011.943480 fatcat:d2wvloyv6jcbzp2yathd52mx2u

Neuronal Sequence Models for Bayesian Online Inference [article]

Sascha Frölich, Dimitrije Marković, Stefan J. Kiebel
2020 arXiv   pre-print
Importantly, it is promising to translate the key idea of probabilistic inference on sequences to machine learning, in order to address challenges in the real-time recognition of speech and human motion  ...  Combining experimental findings with computational concepts like the Bayesian brain hypothesis and predictive coding leads to the interesting possibility that predictive and inferential processes in the  ...  A heteroclinic network is a dynamic system with semi-stable states (saddle points) which are connected by phase-space trajectories.  ... 
arXiv:2004.00930v1 fatcat:m6nodt3xl5adrns3zqdgmqruem

Evolutionary Robotics and Neuroscience [chapter]

2014 The Horizons of Evolutionary Robotics  
The underlying 'electrical' network is a discrete time step, recurrent neural network with a variable number of nodes.  ...  the neural system to cope with an arbitrary robotic system.  ... 
doi:10.7551/mitpress/8493.003.0003 fatcat:qvhpttno25f4zpjhhjzblesr7q

Design of a robust neural network-based tracking controller for a class of electrically driven nonholonomic mechanical systems

Hui-Min Yen, Tzuu-Hseng S. Li, Yeong-Chan Chang
2013 Information Sciences  
of high-degree time-varying uncertainties.  ...  This class of electrically driven nonholonomic mechanical systems can be perturbed by plant uncertainties, unmodeled time-varying perturbations, and external disturbances.  ...  Acknowledgements The support of this work in part by the National Science Council of the Republic of China under NSC 98-2221-E-006-212-MY3 is gratefully acknowledged.  ... 
doi:10.1016/j.ins.2012.07.053 fatcat:ja53bwskyfchtphta2l6cw4tay
« Previous Showing results 1 — 15 out of 151 results