Proceedings of the International Joint Conference on Neural Networks, 2003.最新文献_第5页

Consciousness and its correlates in awake condition, in different sleep stages and in epilepsy 清醒状态、不同睡眠阶段和癫痫的意识及其相关关系

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223357

P. Fenwick, G. Kostopoulos, L. Liu, A. Ioannides

引用次数: 1

Universal approximation with Fuzzy ART and Fuzzy ARTMAP 模糊ART和模糊ARTMAP的通用逼近

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223712

Stephen J Verzi, G. Heileman, M. Georgiopoulos, G. Anagnostopoulos

引用次数: 16

High speed cellular array computer realizations for low power applications 低功耗应用的高速蜂窝式阵列计算机实现

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223920

M. Laiho, A. Kananen, A. Paasio, K. Halonen

引用次数: 1

Ensemble of classifiers based incremental learning with dynamic voting weight update 基于分类器增量学习与动态投票权更新的集成

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224006

R. Polikar, S. Krause, L. Burd

{"title":"Ensemble of classifiers based incremental learning with dynamic voting weight update","authors":"R. Polikar, S. Krause, L. Burd","doi":"10.1109/IJCNN.2003.1224006","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1224006","url":null,"abstract":"An incremental learning algorithm based on weighted majority voting of an ensemble of classifiers is introduced for supervised neural networks, where the voting weights are updated dynamically based on the current test input of unknown class. The algorithm's dynamic voting weight update feature is an enhancement to our previously introduced incremental learning algorithm, Learn++. The algorithm is capable of incrementally learning new information from additional datasets that may later become available, even when the new datasets include instances from additional classes that were not previously seen. Furthermore, the algorithm retains formerly acquired knowledge without requiring access to datasets used earlier, attaining a delicate balance on the stability-plasticity dilemma. The algorithm creates additional ensembles of classifiers based on an iteratively updated distribution function on the training data that favors training with increasingly difficult to learn, previously not learned and/or unseen instances. The final classification is made by weighted majority voting of all classifier outputs in the ensemble, where the voting weights are determined dynamically during actual testing, based on the estimated performance of each classifier on the current test data instance. We present the algorithm in its entirety, as well as its promising simulation results on two real world applications.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"18 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134499686","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: 11

Competitive reinforcement learning in continuous control tasks 连续控制任务中的竞争性强化学习

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223699

Myriam Abramson, P. Pachowicz, H. Wechsler

{"title":"Competitive reinforcement learning in continuous control tasks","authors":"Myriam Abramson, P. Pachowicz, H. Wechsler","doi":"10.1109/IJCNN.2003.1223699","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223699","url":null,"abstract":"This paper describes a novel hybrid reinforcement learning algorithm, Sarsa Learning Vector Quantization (SLVQ), that leaves the reinforcement part intact but employs a more effective representation of the policy function using a piecewise constant function based upon \"policy prototypes\". The prototypes correspond to the pattern classes induced by the Voronoi tessellation generated by self-organizing methods like Learning Vector Quantization (LVQ). The determination of the optimal policy function can be now viewed as a pattern recognition problem in the sense that the assignment of an action to a point in the phase space is similar to the assignment of a pattern class to a point in phase space. The distributed LVQ representation of the policy function automatically generates a piecewise constant tessellation of the state space and yields in a major simplification of the learning task relative to the standard reinforcement learning algorithms for whom a discontinuous table look function has to be learned. The feasibility and comparative advantages of the new algorithm is shown on the cart centering and mountain car problems, two control problems of increased difficulty.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131311725","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: 9

Combinative neural-network-based classifiers for optical handwritten character and letter recognition 基于组合神经网络的光学手写体字符和字母识别分类器

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223757

G. Daqi, Xie Chao, Nie Guiping

引用次数: 7

Autonomous diagnostics and prognostics through competitive learning driven HMM-based clustering 通过竞争性学习驱动的基于hmm的聚类进行自主诊断和预测

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223951

R. Chinnam, Pundarikaksha Baruah

引用次数: 55

Binary image coding using cellular neural networks 二值图像的细胞神经网络编码

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223853

D. Feiden, R. Tetzlaff

引用次数: 3

An adaptive sub-space filter model 一种自适应子空间滤波模型

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223912

A. Zaknich

{"title":"An adaptive sub-space filter model","authors":"A. Zaknich","doi":"10.1109/IJCNN.2003.1223912","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223912","url":null,"abstract":"A tunable approximate piecewise linear regression model [A. Zaknich, Y. Attikiouzel, December 2000] has been previously developed, which can be adjusted by a single smoothing parameter continuously from the best piecewise linear model in each sub-space to the best approximate piecewise linear model over the whole data space. A suitable value in between ensures that all neighbouring piecewise linear models merge together smoothly at their boundaries. This model was developed by making relatively minor changes to the form of the modified probabilistic neural network [A. Zaknich, July 1998], a network used for general nonlinear regression. The special modified probabilistic neural network (MPNN) structure allows it to be easily used to model a process by appropriately weighting piecewise linear models associated with each piecewise linear models associated with each of the network's radial basis functions, which together cover the data space. The model has now bee further extended to allow each piecewise linear model section to be adapted separately as new data flows through it. By doing this, the proposed adaptive sub-space filter (ASF) model represents a learning/filtering method for nonlinear processes that provides a solution to the stability/plasticity dilemma associated with standard adaptive filters.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115468433","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: 0

Firing correlations improve detection of moving bars 发射相关性提高了对移动杆的检测

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223877

Garrett T. Kenyon, J. Theiler, D. Marshak, B. Moore, J. Jeffs, B. Travis

引用次数: 1