检索结果-南通市图书馆

Chinese Physics B 2010年第11期19卷 212-217页

作者：邵海见蔡国梁汪浩祥 Nonlinear Scientific Research Center Jiangsu University

In this study, a successful linear matrix inequality approach is used to analyse a non-parameter perturbation of multi-delay hopfield neural network by constructing an appropriate Lyapunov-Krasovskii functional. This ... 详细信息

关键词： hopfield neural network LMI approach global synchronisation sliding mode control

ON THE ASYMPTOTIC BEHAVIOR OF hopfield neural network WITH PERIODIC INPUTS

在线全文

学校读者我要写书评

暂无评论

Applied Mathematics and Mechanics(English Edition) 2002年第12期23卷 1367-1373页

作者：向兰周进刘曾荣孙姝 Department of Physics Hebei University of Technology Department of Mathematics Shanghai University Shanghai 200436 P R China Department of Mathematics Shanghai University Naval Submarine Academy

Without assuming the boundedness and differentiability of the nonlinear activation functions, the new sufficient conditions of the existence and the global exponential stability of periodic solutions for hopfield neural network with periodic inputs are given by using Mawhin's coincidence degree theory and Liapunov's function method.

关键词： hopfield neural network periodic solution global exponential stability coincidence degree Liapunov's function

Improvement of the hopfield neural network by MC-Adaptation Rule

在线全文

学校读者我要写书评

暂无评论

Chinese Physics Letters 2006年第6期23卷 1402-1405页

作者：周震赵鸿 Department of Physics Xiamen University Xiamen 361005

We show that the performance of the hopfield neural networks, especially the quality of the recall and the capacity of the effective storing, can be greatly improved by making use of a recently presented neural network designing method without altering the whole structure of the network. In the improved neural network, a memory pattern is recalled exactly from initial states having a given degree of similarity with the memory pattern, and thus one can avoids to apply the overlap criterion as carried out in the hopfield neural networks.

关键词： hopfield neural network MC-Adaptation Rule

Filtering and Estimation of Vehicular Dead Reckoning System Based on hopfield neural network

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2003年第3期12卷 230-235页

作者：毕军付梦印张启鸿 Department of Automatic Control School of Information Science and TechnologyBeijing Institute of Technology

The algorithm of hopfield neural network filtering and estimation is studied. The model of vehicular dead reckoning system fitting for the algorithm is constructed, and the design scheme of system filtering and estimation based on hopfield network is proposed. Compared with Kalman filter, the algorithm does not require very precise system model and the prior knowledge of noise statistics and does not diverge easily. The simulation results show that the vehicular dead reckoning system based on hopfield network filtering and estimation has the good position precision, and needn't require the inertial sensors with high precision. Therefore, the algorithm has the good practicability.

关键词： hopfield neural network dead reckoning filtering and estimation vehicle navigation

Dynamic pricing by hopfield neural network

在线全文

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2004年第3期11卷 291-294页

作者： Lusajo M Minga 冯玉强李一军路杨 Kimutai Kimeli School of Management Harbin Institute of Technology Harbin 150001 China Dept. of Computer Science and Engineering Harbin Institute of Technology Harbin 150001 China

The increase in the number of shopbots users in e-commerce has triggered flexibility of sellers in their pricing strategies. Sellers see the importance of automated price setting which provides efficient services to a large number of buyers who are using shopbots. This paper studies the characteristic of decreasing energy with time in a continuous model of a hopfield neural network that is the decreasing of errors in the network with respect to time. The characteristic shows that it is possible to use hopfield neural network to get the main factor of dynamic pricing; the least variable cost, from production function principles. The least variable cost is obtained by reducing or increasing the input combination factors, and then making the comparison of the network output with the desired output, where the difference between the network output and desired output will be decreasing in the same manner as in the hopfield neural network energy. hopfield neural network will simplify the rapid change of prices in e-commerce during transaction that depends on the demand quantity for demand sensitive model of pricing.

关键词： E-commerce dynamic pricing production function hopfield neural network

System Parameter Identification Experiment Based on hopfield neural network for Self Balancing Vehicle

在线全文

学校读者我要写书评

暂无评论

System Parameter Identification Experiment Based on Hopfield...

A hopfield neural network Algorithm for Automatic Name Placement for Point Feature

第36届中国控制会议

作者： Yuan Song Bin Xing Lei Guo Xiao Xu School of Automation Beijing University of Posts and Telecommunications

ISBN: (纸本)9781538629185

In recent years,the system parameter identification attracts attention of scholars and engineers,as the system control precision can be improved with *** this paper,we take advantage of Hopfleld neural network to identify the system ***,a kind of self balancing vehicle dynamic model is ***,the subsystem of the self balancing vehicle is analyzed in the form of Hopfleld neural ***,taking the actual parameter into the dynamic model,the simulation of the system parameter identification is *** the simulation result,there are errors between the actual value deviation and the system parameter identification result achieved in the paper,but it is within the acceptable range,so the identification results are acceptable.

关键词： Parameter Identification hopfield neural network Self Balancing Vehicle

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Geo-Spatial Information Science 2004年第2期7卷 144-147页

作者： FANHong TANGGuoqiang ZHANGZuxun DUDaosheng professor Ph.DStateKeyLaboratoryofInformationEngineeringinSurveyingMappingandRemoteSensingWuhanUniversity129LuoyuRoadWuhan430079China. 不详

This paper presents a method of adding label to the map especially for the point feature. This method overcomes the shortcoming of traditional methods, e.g. Conflict\|Backtracking method. Its kernel algorithm use the hopfield neural network to find the best label position for point feature. The experimental results proves that this algorithm has good permanence and high speed.

关键词： hopfield neural network energy function map name placement

Existence and Exponential Stability of Almost Periodic Solution for hopfield neural network Equations with Almost Periodic Imput

在线全文

学校读者我要写书评

暂无评论

Northeastern Mathematical Journal 2006年第2期22卷 199-205页

作者：杨喜陶 Department of Mathematics Hunan University of Science and Technology XiangtanHunan Province411201

By constructing Liapunov functions and building a new inequality, we obtain two kinds of sufficient conditions for the existence and global exponential stability of almost periodic solution for a hopfield-type neural networks subject to almost periodic external stimuli. Irt this paper, we assume that the network parameters vary almost periodically with time and we incorporate variable delays in the processing part of the network architectures.

关键词： hopfield neural network almost periodic solution exponential stability,Liapunov function

Automatic Sleep Stage Classification for Daytime Nap Based on hopfield neural network

在线全文

学校读者我要写书评

暂无评论

Automatic Sleep Stage Classification for Daytime Nap Based o...

Stabilization of distributed parameters type hopfield neural network with damped stochastic disturbance

第25届中国控制与决策会议

作者： Xi Chen Bei Wang Xingyu Wang Key Laboratory of Advanced Control and Optimization for Chemical Processes (East China University of Science and Technology) Ministry of Education School of Information Science and Engineering East China University of Science and Technology

ISBN: (纸本)9781467355339

In this study, automatic method of sleep stage classification for daytime nap is investigated. The ultimate objective is to identify the changing of sleep level during one’s nap. The sleep data is recorded according to the polysomnographic （PSG） measurement. The Electroencephalograph （EEG） is analyzed for sleep stage classification. Totally, 4 parameters are selected and calculated for each 20-second segment of EEG data. The main method is based on hopfield neural network （HNN）. The neural network is trained by using standard mode. The sleep stages are classified based on HNN for each consecutive segment. The obtained result showed about 80.6% consistence comparing with the visual inspection. The automatic classification results indicated the changing of sleep level during nap, which can be useful for daytime nap sleep evaluation.

关键词： Sleep Stage Determination Daytime Nap EEG hopfield neural network

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Stabilization of distributed parameters type Hopfield neural...