检索结果-内蒙古大学图书馆

Leveraging partially overlapping channels for intra-and inter-coalition communication in cooperative UAV swarms

Science China(Information Sciences) 2021年第4期64卷 68-83页

作者： Kailing YAO Yuhua XU Hong LI Jin CHEN Shihua ZHANG Xingyue YU College of Communications Engineering PLA Army Engineering University Nanjing Military Representative Bureau of PLA Rocket Force

Cooperative UAV swarms typically adopt coalition-based network structures for executing tasks more efficiently. Coalition heads in such networks need to do both intra-and inter-coalition communication and may operate on different channels. While being equipped with multiple transceivers or switching among channels are alternative methods, this option would result in larger payload or incur delays. Fortunately,partially overlapping channels(POCs) can be used to forward messages on different channels since communication can be made on adjacent overlapped channels. This can help realize both intra-and inter-coalition communication with heads being equipped with only one transceiver and no switching. Therefore, this paper proposes a POC-based communication method where each coalition selects one of the POCs and UAVs in the same coalition operating on the same channel. While POCs enable information exchange among coalitions,they also incur inter-coalition interference and therefore the POC access problem is investigated. Owing to the coupled relationships among the strategies of coalitions, the problem is a combinatorial optimization one and an online learning algorithm is proposed. The algorithm is distributed and reduces the computation complexity to a great extent. Based on the knowledge of the potential game theory, the algorithm is proved to converge to the optimal solution of each stage asymptotically. Under three representative settings,simulations are made to verify the effectiveness of the proposed method.

关键词： UAV swarm coalition partially overlapping channel learning algorithm game theory

来源：评论

学校读者我要写书评

暂无评论

The ContexTable: Building and Testing an Intelligent, Context-Aware Kitchen Table

The ContexTable: Building and Testing an Intelligent, Contex...

引用

作者： Hoopes, Daniel M. Brigham Young University

学位级别：M.Sc.

The purpose of this thesis was to design and evaluate The ContexTable, a context-aware system built into a kitchen table. After establishing the current status of the field of context-aware systems and the hurdles and problems being faced, a functioning prototype system was designed and built. The prototype makes it possible to explore established, untested theory and novel solutions to problems faced in the field.

关键词： human computer interaction context aware HCI LabVIEW data acquisition sensors kitchen table home context situated computing learning algorithm AI artificial intelligence pattern matching home automation blank slate tabula rasa formative evaluation qualitative analysis hardware software National Instruments

来源：评论

学校读者我要写书评

暂无评论

Training feedforward neural nets in Hopfield-energy-based configuration: A two-step approach

引用

PATTERN RECOGNITION 2024年 145卷

作者： Wang, Jing Chen, Jiahong Zhang, Kuangen Sigal, Leonid Univ British Columbia Dept Mech Engn Vancouver BC Canada Univ British Columbia Dept Comp Sci Vancouver BC Canada

We introduce Hopfield-Energy-Based learning, a general learning framework that is inspired by energy-based models, to train feedforward neural nets. Our approach includes two training phases applied iteratively: first, the minimization of the internal energy, which captures dependencies between input samples and network parameters, is carried out in an unsupervised manner;second, the problem-dependent supervised external energy (e.g., cross-entropy loss) combined with partially reversed internal energy gradients are back-propagated in a standard manner. The intuition is that the first stage helps parameters to settle into the state that simply partitions data into clusters;while in the second stage, the network is allowed to deviate from that clustering a bit (hence gradient reversal) in order to converge to parameters that ultimately perform well on the task at hand. Notably, the data used for the two steps might not be one and the same (e.g., can come from different domains) and the approach naturally tailors itself to solve unsupervised domain adaptation problems without adopting any distribution alignment techniques. We also show that the proposed training strategy substantially improves the performance of several ConvNets on standard supervised classification tasks;showing improvements of at least 1.2% (2.64% on CIFAR-10, 4.5% on CIFAR-100, and 1.35% on ImageNet). Our formulation is general, performs well in practice, and holds promise for scenarios where labeled data is limited.

关键词： Hopfield-based energy Feedforward neural nets learning algorithm Supervised learning Unsupervised domain adaptation Computer vision

来源：评论

学校读者我要写书评

暂无评论

MODEL AND algorithm OF NEURAL NETWORKS WITH QUANTUM GATED NODES

引用

NEURAL NETWORK WORLD 2010年第2期20卷 189-206页

作者： Li, Panchi Song, Kaoping Yang, Erlong Daqing Petr Inst Sch Comp & Informat Technol Daqing 163318 Peoples R China Daqing Petr Inst Sch Petr Engn Daqing 163318 Peoples R China

On the basis of analyzing the principles of the quantum rotation gates and quantum controlled-NOT gates, an improved design for CNOT gated quantum neural networks model is proposed and a smart algorithm for it is derived in our paper, based on the gradient descent algorithm. In the improved model, the input information is expressed by the qubits, which, as the control qubits after being rotated by the rotation gate, control the qubits in the hidden layer to reverse. The qubits in the hidden layer, as the control qubits after being rotated by the rotation gate, control the qubits in the output layer to reverse. The networks output is described by the probability amplitude of state |1 > in the output layer. It has been shown in two application examples of pattern recognition and function approximation that the proposed model is superior to the standard error back-propagation networks with regard to their convergence rate, number of iterations, approximation ability, and robustness.

关键词： Quantum computing quantum gates quantum neuron quantum neural networks learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Training trajectories by continuous recurrent multilayer networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2002年第2期13卷 283-291页

作者： Leistritz, L Galicki, M Witte, H Kochs, E Friedrich Schiller Univ Jena Inst Med Stat Comp Sci & Documentat D-07740 Jena Germany Tech Univ Dept Anesthesiol Munich Germany

This paper addresses the problem of training trajectories by means of continuous recurrent neural networks whose feedforward parts are multilayer perceptrons. Such networks can approximate a general nonlinear dynamic system with arbitrary accuracy. The learning process is transformed into an optimal control framework where the weights are the controls to be determined. A training algorithm based upon a variational formulation of Pontryagin's maximum principle is proposed for such networks. Computer examples demonstrating the efficiency of the given approach are also presented.

关键词： approximation learning algorithm multilayer perceptron recurrent network target trajectories

来源：评论

学校读者我要写书评

暂无评论

Why is the Rescorla-Wagner model so influential?

引用

NEUROBIOLOGY OF learning AND MEMORY 2023年第1期204卷 107794页

作者： Soto, Fabian A. Vogel, Edgar H. Uribe-Bahamonde, Yerco E. Perez, Omar D. Florida Int Univ Miami FL 33199 USA Univ Talca Fac Psychol Res Ctr Cognit Sci Talca Chile Univ Talca Fac Psychol Appl Psychol Ctr Talca Chile Univ Talca Talca Chile Univ Chile Dept Ind Engn Santiago Chile Inst Sistemas Complejos Ingn Santiago Chile

The influence of the Rescorla-Wagner model cannot be overestimated, despite that (1) the model does not differ much computationally from its predecessors and competitors, and (2) its shortcomings are well-known in the learning community. Here we discuss the reasons behind its widespread influence in the cognitive and neural sciences, and argue that it is the constant search for general-process theories by learning scholars which eventually produced a model whose application spans many different areas of research to this day. We focus on the theoretical and empirical background of the model, the theoretical connections that it has with later developments across Marr's levels of analysis, as well as the broad variety of research that it has guided and inspired.

关键词： Rescorla-Wagner Prediction error learning rules Computational Pavlovian conditioning Reinforcement Supervised learning learning algorithm

来源：评论

学校读者我要写书评

暂无评论

K-NN based neuro-fuzzy system for time series prediction

K-NN based neuro-fuzzy system for time series prediction

引用

14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2013

作者： Wei, Chia-Ching Chen, Thao-Tsen Lee, Shie-Jue Department of Electrical Engineering National Sun Yat-Sen University Kaohsiung 80424 Taiwan

ISBN: (纸本)9780769550053

Neuro-fuzzy systems have been proposed for different applications for many years. In this paper, a k-NN based neuro-fuzzy predictor is developed for time series prediction. We use a neuro-fuzzy system to generate prediction results. A set of fuzzy rules can be generated by a self-constructing clustering method. These rules can be refined by a hybrid learning algorithm. In stead of using all training data to training a model, we utilize the k-NN method to dynamically select k instances for each prediction. Experimental results show that our approach can provide more accurate predictions than other methods. © 2013 IEEE.

关键词： kNN based method learning algorithm Neuro-fuzzy system time series

来源：评论

学校读者我要写书评

暂无评论

Using feedback for coherent control of quantum systems

引用

JOURNAL OF OPTICS B-QUANTUM AND SEMICLASSICAL OPTICS 2002年第3期4卷 R35-R52页

作者： Weinacht, TC Bucksbaum, PH Univ Michigan Ann Arbor MI 48109 USA

A longstanding goal in chemical physics has been the control of atoms and molecules using coherent light fields. This paper provides a brief overview of the field and discusses experiments that use a programmable pulse shaper to control the quantum state of electronic wavepackets in Rydberg atoms and electronic and nuclear dynamics in molecular liquids. The shape of Rydberg wavepackets was controlled by using tailored ultrafast pulses to excite a beam of caesium atoms. The quantum state of these atoms was measured using holographic techniques borrowed from optics. The experiments with molecular liquids involved the construction of an automated learning machine. A genetic algorithm directed the choice of shaped pulses which interacted with the molecular system inside a learning control loop. Analysis of successful pulse shapes that were found by using the genetic algorithm yield insight into the systems being controlled.

关键词： coherent control feedback ultrafast quantum state preparation learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A type-3 fuzzy control for current sharing and voltage balancing in microgrids

引用

APPLIED SOFT COMPUTING 2022年第0期129卷

作者： Taghieh, Amin Mohammadzadeh, Ardashir Zhang, Chunwei Kausar, Nasreen Castillo, Oscar Shenyang Univ Technol Multidisciplinary Ctr Infrastruct Engn Shenyang 110870 Peoples R China Yildiz Tech Univ Fac Arts & Sci Dept Math TR-34210 Istanbul Turkey Tijuana Inst Technol Div Grad Studies & Res Tijuana Mexico

This paper studies the current sharing and voltage balancing problems of direct current microgrids (DC-MGs) consisting of distributed generation units (DGUs) connected by a communication network. The main challenge is that the DC-MG model is prone to unknown dynamic models and external disturbances. Moreover, the voltage at each DGU's point of coupling (PC) has to converge to its desired value while the information of the DGU filter current is exchanged with the nearest neighbors. To this end, the suggested distributed control algorithm benefits from an interval type-3 fuzzy logic system (IT3FLS). To enhance the accuracy of the approximation, a learning strategy is designed based on a correntropy unscented Kalman filter (CUKF) with a fuzzy kernel size. Utilizing the approximation technique and merging the consensus-based secondary control policy with the proposed type-3 fuzzy (T3F) controller result in the balanced voltages of the closed-loop DC-MG. The convergence of the trajectories of the DC-MG is ensured and the effects of approximation error signals are investigated via the proposed method. Furthermore, the robustness of the voltages and currents against unknown uncertainties admits the efficiency of the suggested learning-based control policy. The simulation results also confirm the appropriate transient response and the robustness of trajectories, thus the suggested controller can be implemented for practical cases. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Microgrid Current sharing Voltage balancing Type-3 fuzzy logic learning algorithm Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Data based Model Constructive Identification -Overcoming the Curse of Dimensionality

引用

IFAC Proceedings Volumes 2000年第28期33卷 1-12页

作者： C.J. Harris X. Hong ISIS Research Group Dept of Electronics and Computer Science University of Southampton Southampton S017 1BJ UK

The modelling of a nonlinear stochastic dynamical processes from data involves solving the problems of data gathering, preprocessing, model architecture selection, learning or adaptation, parametric evaluation and model validation. For a given model architecture such as associative memory networks, a common problem in non-linear modelling is the problem of the curse of dimensionality . A series of complementary data based constructive identification schemes, mainly based on but not limited to an operating point dependent fuzzy models, are introduced in this paper with the aim to overcome the curse of dimensionality. These include (i) a mixture of experts algorithm based on a forward constrained regression algorithm; (ii) an inherent parsimonious delaunay input space partition based piecewise local lineal modelling concept; (iii) a neurofuzzy model constructive approach based on forward orthogonal least squares and optimal experimental design and finally (iv) the neurofuzzy model construction algorithm based on basis functions that are Bézier Bernstein polynomial functions and the additive decomposition. Illustrative examples demonstrate their applicability, showing that the final major hurdle in data based modelling has almost been removed.

关键词： neurofuzzy network system identification nonlinear modelling learning algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：