IEEE transactions on neural networks最新文献_第9页

Zhang neural network versus gradient neural network for solving time-varying linear inequalities. 张神经网络与梯度神经网络求解时变线性不等式。

IEEE transactions on neural networks Pub Date : 2011-10-01 Epub Date: 2011-08-15 DOI: 10.1109/TNN.2011.2163318

Lin Xiao, Yunong Zhang

引用次数: 111

Observer design for switched recurrent neural networks: an average dwell time approach. 切换递归神经网络的观测器设计:平均停留时间方法。

IEEE transactions on neural networks Pub Date : 2011-10-01 Epub Date: 2011-08-04 DOI: 10.1109/TNN.2011.2162111

Jie Lian, Zhi Feng, Peng Shi

引用次数: 109

Online identification of nonlinear spatiotemporal systems using kernel learning approach. 非线性时空系统的核学习在线辨识。

IEEE transactions on neural networks Pub Date : 2011-09-01 Epub Date: 2011-07-22 DOI: 10.1109/TNN.2011.2161331

Hanwen Ning, Xingjian Jing, Li Cheng

{"title":"Online identification of nonlinear spatiotemporal systems using kernel learning approach.","authors":"Hanwen Ning, Xingjian Jing, Li Cheng","doi":"10.1109/TNN.2011.2161331","DOIUrl":"https://doi.org/10.1109/TNN.2011.2161331","url":null,"abstract":"The identification of nonlinear spatiotemporal systems is of significance to engineering practice, since it can always provide useful insight into the underlying nonlinear mechanism and physical characteristics under study. In this paper, nonlinear spatiotemporal system models are transformed into a class of multi-input-multi-output (MIMO) partially linear systems (PLSs), and an effective online identification algorithm is therefore proposed by using a pruning error minimization principle and least square support vector machines. It is shown that many benchmark physical and engineering systems can be transformed into MIMO-PLSs which keep some important physical spatiotemporal relationships and are very helpful in the identification and analysis of the underlying system. Compared with several existing methods, the advantages of the proposed method are that it can make full use of some prior structural information about system physical models, can realize online estimation of the system dynamics, and achieve accurate characterization of some important nonlinear physical characteristics of the system. This would provide an important basis for state estimation, control, optimal analysis, and design of nonlinear distributed parameter systems. The proposed algorithm can also be applied to identification problems of stochastic spatiotemporal dynamical systems. Numeral examples and comparisons are given to demonstrate our results.","PeriodicalId":13434,"journal":{"name":"IEEE transactions on neural networks","volume":"22 9","pages":"1381-94"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TNN.2011.2161331","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"30030839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 25

New accurate and flexible design procedure for a stable KWTA continuous time network. 新的精确和灵活的设计程序稳定KWTA连续时间网络。

IEEE transactions on neural networks Pub Date : 2011-09-01 Epub Date: 2011-07-14 DOI: 10.1109/TNN.2011.2154340

Ruxandra L Costea, Corneliu A Marinov

{"title":"New accurate and flexible design procedure for a stable KWTA continuous time network.","authors":"Ruxandra L Costea, Corneliu A Marinov","doi":"10.1109/TNN.2011.2154340","DOIUrl":"https://doi.org/10.1109/TNN.2011.2154340","url":null,"abstract":"The classical continuous time recurrent (Hopfield) network is considered and adapted to K -winner-take-all operation. The neurons are of sigmoidal type with a controllable gain G, an amplitude m and interconnected by the conductance p. The network is intended to process one by one a sequence of lists, each of them with N distinct elements, each of them squeezed to [0,I] admission interval, each of them having an imposed minimum separation between elements z(min). The network carries out: 1) a matching dynamic process between the order of list elements and the order of outputs, and 2) a binary type steady-state separation between K and K+1 outputs, the former surpassing a +ξ threshold and the later falling under the -ξ threshold. As a result, the machine will signal the ranks of the K largest elements of the list. To achieve 1), the initial condition of processing phase has to be placed in a computable θ -vicinity of zero-state. This requires a resetting procedure after each list. To achieve 2) the bias current M has to be within a certain interval computable from circuit parameters. In addition, the steady-state should be asymptotically stable. To these goals, we work with high gain and exploit the sigmoid properties and network symmetry. The various inequality type constraints between parameters are shown to be compatible and a neat synthesis procedure, simple and flexible, is given for the tanh sigmoid. It starts with the given parameters N, K, I, z(min), m and computes simple bounds of p, G, ξ, θ, and M. Numerical tests and comments reveal qualities and shortcomings of the method.","PeriodicalId":13434,"journal":{"name":"IEEE transactions on neural networks","volume":"22 9","pages":"1357-67"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TNN.2011.2154340","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"30013312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Nonlinear identification with local model networks using GTLS techniques and equality constraints. 基于GTLS技术和等式约束的局部模型网络非线性辨识。

IEEE transactions on neural networks Pub Date : 2011-09-01 Epub Date: 2011-07-22 DOI: 10.1109/TNN.2011.2159309

Christoph Hametner, Stefan Jakubek

引用次数: 28

Comprehensive review of neural network-based prediction intervals and new advances. 基于神经网络的预测区间及其新进展综述。

IEEE transactions on neural networks Pub Date : 2011-09-01 Epub Date: 2011-07-29 DOI: 10.1109/TNN.2011.2162110

Abbas Khosravi, Saeid Nahavandi, Doug Creighton, Amir F Atiya

{"title":"Comprehensive review of neural network-based prediction intervals and new advances.","authors":"Abbas Khosravi, Saeid Nahavandi, Doug Creighton, Amir F Atiya","doi":"10.1109/TNN.2011.2162110","DOIUrl":"https://doi.org/10.1109/TNN.2011.2162110","url":null,"abstract":"This paper evaluates the four leading techniques proposed in the literature for construction of prediction intervals (PIs) for neural network point forecasts. The delta, Bayesian, bootstrap, and mean-variance estimation (MVE) methods are reviewed and their performance for generating high-quality PIs is compared. PI-based measures are proposed and applied for the objective and quantitative assessment of each method's performance. A selection of 12 synthetic and real-world case studies is used to examine each method's performance for PI construction. The comparison is performed on the basis of the quality of generated PIs, the repeatability of the results, the computational requirements and the PIs variability with regard to the data uncertainty. The obtained results in this paper indicate that: 1) the delta and Bayesian methods are the best in terms of quality and repeatability, and 2) the MVE and bootstrap methods are the best in terms of low computational load and the width variability of PIs. This paper also introduces the concept of combinations of PIs, and proposes a new method for generating combined PIs using the traditional PIs. Genetic algorithm is applied for adjusting the combiner parameters through minimization of a PI-based cost function subject to two sets of restrictions. It is shown that the quality of PIs produced by the combiners is dramatically better than the quality of PIs obtained from each individual method.","PeriodicalId":13434,"journal":{"name":"IEEE transactions on neural networks","volume":"22 9","pages":"1341-56"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TNN.2011.2162110","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"29902224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 481

Discriminative graph embedding for label propagation. 标签传播的判别图嵌入。

IEEE transactions on neural networks Pub Date : 2011-09-01 Epub Date: 2011-07-22 DOI: 10.1109/TNN.2011.2160873

Canh Hao Nguyen, Hiroshi Mamitsuka

{"title":"Discriminative graph embedding for label propagation.","authors":"Canh Hao Nguyen, Hiroshi Mamitsuka","doi":"10.1109/TNN.2011.2160873","DOIUrl":"https://doi.org/10.1109/TNN.2011.2160873","url":null,"abstract":"In many applications, the available information is encoded in graph structures. This is a common problem in biological networks, social networks, web communities and document citations. We investigate the problem of classifying nodes' labels on a similarity graph given only a graph structure on the nodes. Conventional machine learning methods usually require data to reside in some Euclidean spaces or to have a kernel representation. Applying these methods to nodes on graphs would require embedding the graphs into these spaces. By embedding and then learning the nodes on graphs, most methods are either flexible with different learning objectives or efficient enough for large scale applications. We propose a method to embed a graph into a feature space for a discriminative purpose. Our idea is to include label information into the embedding process, making the space representation tailored to the task. We design embedding objective functions that the following learning formulations become spectral transforms. We then reformulate these spectral transforms into multiple kernel learning problems. Our method, while being tailored to the discriminative tasks, is efficient and can scale to massive data sets. We show the need of discriminative embedding on some simulations. Applying to biological network problems, our method is shown to outperform baselines.","PeriodicalId":13434,"journal":{"name":"IEEE transactions on neural networks","volume":"22 9","pages":"1395-405"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TNN.2011.2160873","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"30030840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

A dynamic feedforward neural network based on gaussian particle swarm optimization and its application for predictive control. 基于高斯粒子群优化的动态前馈神经网络及其在预测控制中的应用。

IEEE transactions on neural networks Pub Date : 2011-09-01 Epub Date: 2011-07-29 DOI: 10.1109/TNN.2011.2162341

Min Han, Jianchao Fan, Jun Wang

{"title":"A dynamic feedforward neural network based on gaussian particle swarm optimization and its application for predictive control.","authors":"Min Han, Jianchao Fan, Jun Wang","doi":"10.1109/TNN.2011.2162341","DOIUrl":"https://doi.org/10.1109/TNN.2011.2162341","url":null,"abstract":"A dynamic feedforward neural network (DFNN) is proposed for predictive control, whose adaptive parameters are adjusted by using Gaussian particle swarm optimization (GPSO) in the training process. Adaptive time-delay operators are added in the DFNN to improve its generalization for poorly known nonlinear dynamic systems with long time delays. Furthermore, GPSO adopts a chaotic map with Gaussian function to balance the exploration and exploitation capabilities of particles, which improves the computational efficiency without compromising the performance of the DFNN. The stability of the particle dynamics is analyzed, based on the robust stability theory, without any restrictive assumption. A stability condition for the GPSO+DFNN model is derived, which ensures a satisfactory global search and quick convergence, without the need for gradients. The particle velocity ranges could change adaptively during the optimization process. The results of a comparative study show that the performance of the proposed algorithm can compete with selected algorithms on benchmark problems. Additional simulation results demonstrate the effectiveness and accuracy of the proposed combination algorithm in identifying and controlling nonlinear systems with long time delays.","PeriodicalId":13434,"journal":{"name":"IEEE transactions on neural networks","volume":"22 9","pages":"1457-68"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TNN.2011.2162341","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"29902223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 84

Parallel reservoir computing using optical amplifiers. 使用光放大器的并行库计算。

IEEE transactions on neural networks Pub Date : 2011-09-01 Epub Date: 2011-07-29 DOI: 10.1109/TNN.2011.2161771

Kristof Vandoorne, Joni Dambre, David Verstraeten, Benjamin Schrauwen, Peter Bienstman

{"title":"Parallel reservoir computing using optical amplifiers.","authors":"Kristof Vandoorne, Joni Dambre, David Verstraeten, Benjamin Schrauwen, Peter Bienstman","doi":"10.1109/TNN.2011.2161771","DOIUrl":"https://doi.org/10.1109/TNN.2011.2161771","url":null,"abstract":"Reservoir computing (RC), a computational paradigm inspired on neural systems, has become increasingly popular in recent years for solving a variety of complex recognition and classification problems. Thus far, most implementations have been software-based, limiting their speed and power efficiency. Integrated photonics offers the potential for a fast, power efficient and massively parallel hardware implementation. We have previously proposed a network of coupled semiconductor optical amplifiers as an interesting test case for such a hardware implementation. In this paper, we investigate the important design parameters and the consequences of process variations through simulations. We use an isolated word recognition task with babble noise to evaluate the performance of the photonic reservoirs with respect to traditional software reservoir implementations, which are based on leaky hyperbolic tangent functions. Our results show that the use of coherent light in a well-tuned reservoir architecture offers significant performance benefits. The most important design parameters are the delay and the phase shift in the system's physical connections. With optimized values for these parameters, coherent semiconductor optical amplifier (SOA) reservoirs can achieve better results than traditional simulated reservoirs. We also show that process variations hardly degrade the performance, but amplifier noise can be detrimental. This effect must therefore be taken into account when designing SOA-based RC implementations.","PeriodicalId":13434,"journal":{"name":"IEEE transactions on neural networks","volume":"22 9","pages":"1469-81"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TNN.2011.2161771","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"29902227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 171

Source separation and clustering of phase-locked subspaces. 锁相子空间的源分离与聚类。

IEEE transactions on neural networks Pub Date : 2011-09-01 Epub Date: 2011-07-25 DOI: 10.1109/TNN.2011.2161674

Miguel Almeida, Jan-Hendrik Schleimer, José Mario Bioucas-Dias, Ricardo Vigário

{"title":"Source separation and clustering of phase-locked subspaces.","authors":"Miguel Almeida, Jan-Hendrik Schleimer, José Mario Bioucas-Dias, Ricardo Vigário","doi":"10.1109/TNN.2011.2161674","DOIUrl":"https://doi.org/10.1109/TNN.2011.2161674","url":null,"abstract":"It has been proven that there are synchrony (or phase-locking) phenomena present in multiple oscillating systems such as electrical circuits, lasers, chemical reactions, and human neurons. If the measurements of these systems cannot detect the individual oscillators but rather a superposition of them, as in brain electrophysiological signals (electo- and magneoencephalogram), spurious phase locking will be detected. Current source-extraction techniques attempt to undo this superposition by assuming properties on the data, which are not valid when underlying sources are phase-locked. Statistical independence of the sources is one such invalid assumption, as phase-locked sources are dependent. In this paper, we introduce methods for source separation and clustering which make adequate assumptions for data where synchrony is present, and show with simulated data that they perform well even in cases where independent component analysis and other well-known source-separation methods fail. The results in this paper provide a proof of concept that synchrony-based techniques are useful for low-noise applications.","PeriodicalId":13434,"journal":{"name":"IEEE transactions on neural networks","volume":"22 9","pages":"1419-34"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TNN.2011.2161674","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"30034632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 16