Filters








193,180 Hits in 4.4 sec

Toward V&V of neural network based controllers

Johann Schumann, Stacy Nelson
2002 Proceedings of the first workshop on Self-healing systems - WOSS '02  
Despite the advantages of adaptive neural network based systems, the lack of methods to perform certification, verification, and validation (V&V) of such systems severely restricts their applicability.  ...  In this paper, we report on ongoing work to develop V&V techniques and processes for NN-based safety-critical control systems, in our case an aircraft flight control system.  ...  In this paper, we describe preliminary research results on development of V&V (verification and validation techniques) for a neural network based Intelligent Flight Control System (IFCS).  ... 
doi:10.1145/582128.582141 dblp:conf/woss/SchumannN02 fatcat:iujwu53qdvatbonndrmxfvg2au

Toward V&V of neural network based controllers

Johann Schumann, Stacy Nelson
2002 Proceedings of the first workshop on Self-healing systems - WOSS '02  
Despite the advantages of adaptive neural network based systems, the lack of methods to perform certification, verification, and validation (V&V) of such systems severely restricts their applicability.  ...  In this paper, we report on ongoing work to develop V&V techniques and processes for NN-based safety-critical control systems, in our case an aircraft flight control system.  ...  In this paper, we describe preliminary research results on development of V&V (verification and validation techniques) for a neural network based Intelligent Flight Control System (IFCS).  ... 
doi:10.1145/582129.582141 fatcat:x3nv5n7c3bbodji34yx4bb77su

INFERNO: A Novel Architecture for Generating Long Neuronal Sequences with Spikes [chapter]

Alex Pitti, Philippe Gaussier, Mathias Quoy
2017 Lecture Notes in Computer Science  
We show for the first time that it is possible to stabilize iteratively the long-range control of a recurrent spiking neurons network over long sequences.  ...  As part of the principle of free-energy minimization proposed by Karl Friston, we propose a novel neural architecture to optimize the free-energy inherent to spiking recurrent neural networks to regulate  ...  ANN controls RNN based on error prediction toward targets.  ... 
doi:10.1007/978-3-319-59072-1_50 fatcat:zr6gnq76j5htbjothkvx6l5f3u

Application of Neural Networks in High Assurance Systems: A Survey [chapter]

Johann Schumann, Pramod Gupta, Yan Liu
2010 Studies in Computational Intelligence  
More importantly, we provide an overview of assurance issues and challenges with the neural network model based control scheme.  ...  Artificial Neural Networks (ANNs) are employed in many areas of industry such as pattern recognition, robotics, controls, medicine, and defence.  ...  V&V Approaches for Neural Networks In the following, we will discuss V&V approaches for neural networks and systems, containing neural networks, in particular neuro-adaptive controllers.  ... 
doi:10.1007/978-3-642-10690-3_1 fatcat:4j5jsjrfajfdhefabtf5rhx52a

Intelligent neuro-controller for navigation of mobile robot

Mukesh Kumar Singh, Dayal R. Parhi
2009 Proceedings of the International Conference on Advances in Computing, Communication and Control - ICAC3 '09  
Back propagation method is used to trained the network. This paper analyzes the kinematical modeling of mobile robots as well as the design of control systems for the autonomous motion of the robot.  ...  A four layer neural networks is used to design and develop the neurocontroller to solve the path and time optimization problem of mobile robots which deals the with cognitive tasks such as learning, adaptation  ...  A motion controller based on neural network technique is proposed for navigation of the mobile robot.  ... 
doi:10.1145/1523103.1523129 fatcat:dihdxro3fbb7fjlm5pc6mhtcva

Artificial Neural Network Controller for Automatic Ship Berthing Using Separate Route

Li Qiang, Hong Bi-Guang
2020 Journal of Web Engineering  
In this study, the artificial neural network algorithm has been used to establish an automatic berthing model, based on the scheduled route.  ...  The complexity in the operation of ships in the port, requires control algorithm with multiple input and output for the automatic berthing control of the ship.  ...  neural network controller for automatic ship berthing using Separate route", we declare that we have no conflict of interest.  ... 
doi:10.13052/jwe1540-9589.19788 fatcat:33k34u4omjdirmfv6mq2pezuaa

Interpretable PID Parameter Tuning for Control Engineering using General Dynamic Neural Networks: An Extensive Comparison [article]

Johannes Günther, Elias Reichensdörfer, Patrick M. Pilarski, Klaus Diepold
2020 arXiv   pre-print
This combination of rigorous evaluation paired with better interpretability is an important step towards the acceptance of neural-network-based control approaches.  ...  The neural PID controller performs better than standard PID control in 15 of 16 tasks and better than model-based control in 13 of 16 tasks.  ...  The neural-network-based approach outperforms a standard PID controller in 15 of 16 scenarios and outperforms a model-based controller in 13 of 16 scenarios.  ... 
arXiv:1905.13268v3 fatcat:mcw3hsuhq5arrdvkbqy7uunjsa

Interpretable PID parameter tuning for control engineering using general dynamic neural networks: An extensive comparison

Johannes Günther, Elias Reichensdörfer, Patrick M. Pilarski, Klaus Diepold, Yanzheng Zhu
2020 PLoS ONE  
This combination of rigorous evaluation paired with better interpretability is an important step towards the acceptance of neural-network-based control approaches for real-world systems.  ...  The neural PID controller performs better than standard PID control in 15 of 16 tasks and better than model-based control in 13 of 16 tasks.  ...  The neural-network-based approach outperforms a standard PID controller in 15 of 16 scenarios and outperforms a model-based controller in 13 of 16 scenarios.  ... 
doi:10.1371/journal.pone.0243320 pmid:33301494 fatcat:6as7e5rirrh5xhbyv2o35c5h7i

PSO search for fast face detection with neural networks(Neuro-based Recognition and Control for Alife(OS),Session: TA1-A)

Masanori Sugisaka, Xinjian Fan
2004 The Abstracts of the international conference on advanced mechatronics : toward evolutionary fusion of IT and mechatronics : ICAM  
for Alife(OS) Neurointerface Based on a Virtual Master-Slave Concept and Its Feedback Compensation Rafiudciin Syam, Keigo Watanabe, and Kiyotaka Izumi A design mcthod for neural network (NN) based feedforward  ...  , Xinj ian Fan This paper presents the application efparticle swarm optimization (PSO) to improve the search speed of neuraa network based face detection  ... 
doi:10.1299/jsmeicam.2004.4.38_2 fatcat:z2f3vfsn25a7npuoublcrdra6m

Adaptive Neural Sliding Mode Control of Active Power Filter

Juntao Fei, Zhe Wang
2013 Journal of Applied Mathematics  
The advantages of the adaptive control, neural network control, and sliding mode control are combined together to achieve the control task; that is, the harmonic current of nonlinear load can be eliminated  ...  Sliding surface coordinate function and sliding mode controller are used as input and output of the RBF neural network, respectively.  ...  Research Foundation of High-Level Innovation and Entrepreneurship Plan of Jiangsu Province.  ... 
doi:10.1155/2013/341831 fatcat:styd64ozwrcxpfgsdf4h67ojza

Mixed-signal neuron-synapse implementation for large-scale neural network

Il Song Han
2006 Neurocomputing  
This paper describes a new mixed-signal VLSI implementation of neural networks for low power and asynchronous operation.  ...  The linearised transconductance produces the synaptic function of multiplication, weight programming, and summation of synaptic currents for the neuron.  ...  Key words : Analogue -mixed VLSI neural network, pulse/spike-based neural computation, asynchronous operation, MOSFET resistance , voltage-controlled linear resistance I.  ... 
doi:10.1016/j.neucom.2005.11.013 fatcat:r4th2l4qbndnfoxtw3pasl4coe

Visual Perception based Motion Planning of Mobile Robot using Road Sign

Pradipta KDas, S. C. Mandhata, H.S Behera, S.N. Patro
2012 International Journal of Computer Applications  
In this paper a new method of road map based navigation is proposed. A vision based motion planning of a mobile robot is implemented in a predefined road map.  ...  In our realization the robot moves towards a junction and at each junction takes a photograph of the road sign map and an image matching algorithm is performed at the host machine to compare the captured  ...  Based on analysis mentioned above, Hopfield neural network energy function corresponding to image matching based on Hausdorff distance is defined as V B R H i x dis V V E xi x i x i xi x i xi     ... 
doi:10.5120/7422-0374 fatcat:ewfwji3ykjczdf2dgmyohx4nli

Toward Verification and Validation of Adaptive Aircraft Controllers

J. Schumann, P. Gupta, S. Jacklin
2005 2005 IEEE Aerospace Conference  
In this paper, we will describe our approach toward V&V of neuro-adaptive controllers.  ...  Control systems with components that can adapt toward changes in the plant, e.g., using a neural network, have been actively investigated as they offer many advantages (e.g., better performance, controllability  ...  In this paper, we will describe our approach to verification and validation of adaptive controllers, which are based upon neural networks (NN).  ... 
doi:10.1109/aero.2005.1559606 fatcat:d6v5fum6infivjfqx372h5kr4a

Cascade Hopfield Neural Network Model and Application in Robot Moving Process

Yu Lianzhi, Liang Weichong
2012 Procedia Engineering  
Based on the principle of discrete Hopfield neural network, the paper proposes a cascade Hopfield neural network controller model and applied in a miniature inchworm robot locomotion process.  ...  The convergence results prove the cascade Hopfield neural network controller is suitable for the orderly continuous moving process of an inchworm robot.  ...  Acknowledgements This study was supported by the Scientific and Innovation Program of Education Commission of Shanghai (No. 10YZ103)  ... 
doi:10.1016/j.proeng.2012.01.047 fatcat:gatkbideojg2fj344t5oimppiy

Tuning Artificial Neural Network Controller Using Particle Swarm Optimization Technique for Nonlinear System [chapter]

Sabrine Slama, Ayachi Errachdi, Mohamed Benrejeb
2021 Deep Learning Applications  
Further, a PSO based neural network controller is also developed to be integrated with the designed system to control a nonlinear systems.  ...  This chapter proposes an optimization technique of Artificial Neural Network (ANN) controller, of single-input single-output time-varying discrete nonlinear system.  ...  The output of the neural network controller is given by the following equation uk ðÞ¼λ c s X n 4 j¼1 v 1j sh cj ÀÁ ! ¼ λ c s X n 4 j¼1 v 1j s X n 3 i¼1 v ji x 1i ! !  ... 
doi:10.5772/intechopen.96424 fatcat:7x6zhmtoffdp7i4jqiebbrexcq
« Previous Showing results 1 — 15 out of 193,180 results