Filters








11,109 Hits in 4.6 sec

Electrohydraulic Control Using Neural MRAC Based on a Modified State Observer

Yang Yang, S. N. Balakrishnan, L. Tang, R. G. Landers
2013 IEEE/ASME transactions on mechatronics  
The neural network adaptation rule is derived using Lyapunov theory, which guarantees stability of the error dynamics and boundedness of the neural network weights.  ...  Stable tracking of a desired trajectory can be achieved for nonlinear systems having significant uncertainties.  ...  STABILITY ANALYSIS In this section, the Lyapunov method is used to prove the boundedness of the observer error dynamics.  ... 
doi:10.1109/tmech.2012.2193592 fatcat:no3khyg3zne5vdah7k4ot7wdbi

The Neurocontroller for Satellite Rotation

Nataliya Shakhovska, Sergio Montenegro, Yurii Kryvenchuk, Maryana Zakharchuk
2019 International Journal of Intelligent Systems and Applications  
Two configuration of neural networkfeedforward neural networks with mini-batch descent and modified Elman neural network, are investigated in this work to verify its ability to control the attitude of  ...  The proposed approach provides the architecture of the neural network and the weights among the layers in order to guarantee stability of the system. The accuracy was calculated.  ...  analytical methods for stability [20] , is introduced.  ... 
doi:10.5815/ijisa.2019.03.01 fatcat:rsop4vhnafg37edpov5ndkf2cm

Neuro-physical dynamic load modeling using differentiable parametric optimization [article]

Shrirang Abhyankar, Jan Drgona, Andrew August, Elliot Skomski, Aaron Tuor
2022 arXiv   pre-print
In this work, we investigate a data-driven approach for obtaining a reduced equivalent load model of distribution systems for electromechanical transient stability analysis.  ...  The proposed reduced equivalent is a neuro-physical model comprising of a traditional ZIP load model augmented with a neural network.  ...  ACKNOWLEDGEMENTS This work was supported through the Data Model Convergence (DMC) initiative at Pacific Northwest National Laboratory (PNNL).  ... 
arXiv:2203.10582v1 fatcat:ca46n6anebd63kjix6vtya7u3e

Discovering dynamical features of Hodgkin-Huxley-type model of physiological neuron using artificial neural network [article]

Pavel V. Kuptsov, Nataliya V. Stankevich, Elmira R. Bagautdinova
2022 arXiv   pre-print
From the practical point of view reproducing dynamics with the neural network can be considered as a sort of alternative method of numerical modeling intended for use with contemporary parallel hard- and  ...  For these two systems we create artificial neural networks that are able to reproduce their dynamics.  ...  Acknowledgement Work of PVK on theoretical formulation and numerical computations and work of NVS and ERB on results analysis was supported by grant of Russian Science Foundation No 20-71-10048, https:  ... 
arXiv:2203.14138v1 fatcat:fmenxr7ikze25mzrswghtgsi4m

Training Recurrent Neural Networks via Dynamical Trajectory-Based Optimization [article]

Hamid Khodabandehlou, M. Sami Fadali
2018 arXiv   pre-print
This paper introduces a new method to train recurrent neural networks using dynamical trajectory-based optimization.  ...  The optimization method utilizes a projected gradient system (PGS) and a quotient gradient system (QGS) to determine the feasible regions of an optimization problem and search the feasible regions for  ...  Stability analysis The stability of the training method is a critical issue for any training algorithm.  ... 
arXiv:1805.04152v1 fatcat:jljulygxnfdntk5v2phimlv6pu

Nonlinear Control in the Nematode C. elegans

Megan Morrison, Charles Fieseler, J. Nathan Kutz
2021 Frontiers in Computational Neuroscience  
It remains unclear how a network of neurons can produce fast and slow timescale dynamics that control transitions between stable states in a single model.  ...  Recent whole-brain calcium imaging recordings of the nematode C. elegans have demonstrated that the neural activity associated with behavior is dominated by dynamics on a low-dimensional manifold that  ...  AUTHOR CONTRIBUTIONS MM was the primary producer of the model with input from CF and JK. The figures for the manuscript were created by MM and the content written by MM, CF, and JK.  ... 
doi:10.3389/fncom.2020.616639 pmid:33551783 pmcid:PMC7862714 fatcat:6o6w6effqzaarbzqaauupjzbge

2020 Index IEEE Transactions on Intelligent Vehicles Vol. 5

2020 IEEE Transactions on Intelligent Vehicles  
., +, TIV Sept. 2020 508-518 Auditory Assist Method to Indicate Steering Start Timing in Reverse Parking for Improvement of Driver Performance.  ...  ., +, TIV Dec. 2020 545-555 Automobiles Auditory Assist Method to Indicate Steering Start Timing in Reverse Parking for Improvement of Driver Performance.  ... 
doi:10.1109/tiv.2020.3048338 fatcat:4i46o4q23rftbhh2jzfmbumbey

MALI: A memory efficient and reverse accurate integrator for Neural ODEs [article]

Juntang Zhuang, Nicha C. Dvornek, Sekhar Tatikonda, James S. Duncan
2021 arXiv   pre-print
However, the numerical estimation of the gradient in the continuous case is not well solved: existing implementations of the adjoint method suffer from inaccuracy in reverse-time trajectory, while the  ...  to the adjoint method, and guarantees accuracy in reverse-time trajectory (hence accuracy in gradient estimation).  ...  notations for the ease of analysis.  ... 
arXiv:2102.04668v2 fatcat:rj3xgkn3p5c4db6uz7nhzgrvau

Intelligent Approaches in Locomotion - A Review

Joe Wright, Ivan Jordanov
2014 Journal of Intelligent and Robotic Systems  
We try to compare those methods based on the quality of the produced solutions in terms of time, stability, correctness and the expense and cost for achieving them.  ...  Among the investigated intelligent approaches for solving locomotion problems are oscillator based Central Pattern Generators, Neural Networks, Hidden Markov models, Rule Based and Fuzzy Logic systems,  ...  In more recent times, dissections have enabled a reverse engineering of the neural networks that control this innate locomotion.  ... 
doi:10.1007/s10846-014-0149-z fatcat:wpzs5i4lsbhxfdgkf5i7ij6xa4

An Approach to V&V of Embedded Adaptive Systems [chapter]

Sampath Yerramalla, Yan Liu, Edgar Fuller, Bojan Cukic, Srikanth Gururajan
2004 Lecture Notes in Computer Science  
The Online Stability Monitoring tools based on Lyupunov's Stability Theory detect unstable learning behavior in neural networks.  ...  We apply-our approach to an intelligent flight control system that employs a particular type of Neural Networks (NN) as the adaptive learning paradigm.  ...  The construction of an online stability monitor is based on rigorous mathe matical stability analysis methodology, Lyapunou's direct method [16].  ... 
doi:10.1007/978-3-540-30960-4_12 fatcat:anytwy7yifdwtkir32v45braky

Learning Dynamics Models with Stable Invariant Sets [article]

Naoya Takeishi, Yoshinobu Kawahara
2020 arXiv   pre-print
However, existing methods can only handle the stability of an equilibrium.  ...  It enables us to compute the projection easily, and at the same time, we can maintain the model's flexibility using various invertible neural networks for the transformation.  ...  Also, Chang et al. (2018) discussed reversible neural networks.  ... 
arXiv:2006.08935v2 fatcat:ovchisezfbbqloa74rwqy3z6ra

Nonlinear control in the nematode C. elegans [article]

Megan Morrison, Charles Fieseler, J. Nathan Kutz
2020 arXiv   pre-print
Despite progress in modeling the dynamics with linear or locally linear models, it remains unclear how a single network of neurons can produce the observed features.  ...  Recent whole-brain calcium imaging recordings of the nematode C. elegans have demonstrated that neural activity is dominated by dynamics on a low-dimensional manifold that can be clustered according to  ...  Acknowledgments We are deeply indebted to Manuel Zimmer for the use of his C. elegans datasets in addition to his extensive expertise and insight that contributed to this project.  ... 
arXiv:2001.08332v2 fatcat:ew7rpic2rjc5zm5v3iul5pm66a

The Analysis of Trajectory Control of Non-holonomic Mobile Robots Based on Internet of Things Target Image Enhancement Technology and Backpropagation Neural Network

Lanfei Zhao, Ganlin Wang, Xiaosong Fan, Yufei Li
2021 Frontiers in Neurorobotics  
On this basis, a mobile robot trajectory tracking controller combining the fuzzy algorithm and the neural network is designed to control the linear velocity and angular velocity of the mobile robot.  ...  First, the mathematical kinematics model of the non-holonomic mobile robot is studied. Then, the improved Backpropagation Neural Network (BPNN) is applied to the robot controller.  ...  FUNDING This work was supported by the Fundamental Research Foundation for Universities of Heilongjiang Province (No. LGYC2018JC050).  ... 
doi:10.3389/fnbot.2021.634340 pmid:33828475 pmcid:PMC8020999 fatcat:jqwxjnforrdvlgsa47xumgzxmu

Synthesis and Computer Study of Population Dynamics Controlled Models Using Methods of Numerical Optimization, Stochastization and Machine Learning

Anastasia V. Demidova, Olga V. Druzhinina, Olga N. Masina, Alexey A. Petrov
2021 Mathematics  
A methods for the synthesis of controllers based on the use of artificial neural networks and machine learning are developed.  ...  Theorems on the asymptotic stability of equilibrium states are proved. A qualitative and numerical study of the models is carried out.  ...  Popova for professional guidance and support during the work on this paper. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/math9243303 fatcat:plrjdwzkqvartgelb4kbdxzk5i

Stable memory with unstable synapses

Lee Susman, Naama Brenner, Omri Barak
2019 Nature Communications  
Here we explore the possibility of memory storage within a global component of network connectivity, while individual connections fluctuate.  ...  Our results suggest a link between the properties of learning-rules and those of network-level memory representations, and point at experimentally measurable signatures.  ...  Figure 4a depicts the projections of neural activity on this plane, for two initial conditions (light gray trajectories), both converging to the limit-cycle attractor (dark closed trajectory).  ... 
doi:10.1038/s41467-019-12306-2 pmid:31570719 pmcid:PMC6768856 fatcat:ataanits2zhs5khy6rwiiszm3q
« Previous Showing results 1 — 15 out of 11,109 results