Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.最新文献_第8页

Ability to skip steps emerging from chaotic dynamics 能够跳过从混沌动力学出现的步骤

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555944

Luciana P. P. Bueno, A. Araujo

引用次数: 4

On the design of an ellipsoid ARTMAP classifier within the fuzzy adaptive system ART framework 模糊自适应系统ART框架下椭球ARTMAP分类器的设计

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555876

R. Peralta, G. Anagnostopoulos, E. Gómez-Sánchez, S. Richie

引用次数: 4

Learning of an XOR problem in the presence of noise and redundancy 在存在噪声和冗余的情况下学习异或问题

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556226

D. Cousineau

引用次数: 1

Fast pattern detection using neural networks and cross correlation in the frequency domain 快速模式检测使用神经网络和互相关在频域

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556170

H. El-Bakry, Qiangfu Zhao

引用次数: 16

Blind inversion of Wiener system for single source using nonlinear blind source separation 基于非线性盲源分离的单源维纳系统盲反演

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556030

Zhang Li-sun, De-shuang Huang, Chunhou Zheng, L. Shang

引用次数: 3

Mixture of heterogeneous experts applied to time series: a comparative study 混合异质专家应用于时间序列:比较研究

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556017

W. J. Puma-Villanueva, C. Lima, E.P. dos Santos, F. von Zuben

{"title":"Mixture of heterogeneous experts applied to time series: a comparative study","authors":"W. J. Puma-Villanueva, C. Lima, E.P. dos Santos, F. von Zuben","doi":"10.1109/IJCNN.2005.1556017","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556017","url":null,"abstract":"Prediction models for time series generally include preprocessing followed by the synthesis of an input-output mapping. Neural network models have been adopted to perform both steps, by means of unsupervised and supervised learning, respectively. The flexibility and the generalization capability are the most relevant attributes in favor of connectionist approaches. However, even though time series prediction can be roughly interpreted as learning from data, high levels of performance will solely be achieved if some peculiarities of each time series are properly considered in the design, particularly the existence of trend and seasonality. Instead of directly adopting detrend and/or deseasonality treatments, this paper proposes a novel paradigm for supervised learning based on a mixture of heterogeneous experts. Some mixture models have already been proved to produce good performance as predictors, but the present approach is devoted to a hybrid mixture composed of a set of distinct experts. The purpose is not only to further explore the \"divide-and-conquer\" principle, but also to compare the performance of mixture of heterogeneous experts with the standard mixture of experts approach, using ten distinct time series. The obtained results indicate that mixture of heterogeneous experts generally requires a more elaborate gating device and performs better in the case of more challenging time series.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"8 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121000387","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: 6

fMRI experiments and computational models of the function of the prefrontal cortex and the basal ganglia: a review 前额叶皮层和基底神经节功能的fMRI实验和计算模型:综述

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556116

O. Monchi

引用次数: 0

Fast Bayesian support vector machine parameter tuning with the Nystrom method 快速贝叶斯支持向量机参数调整与Nystrom方法

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556372

C. Gold, Peter Sollich

引用次数: 10

Learning cycles brings chaos in Hopfield networks 学习周期给Hopfield网络带来了混乱

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555949

C. Molter, U. Salihoglu, H. Bersini

引用次数: 0

A multiple BAM for hetero-association and multisensory integration modelling 多元BAM用于异联想和多感觉整合建模

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556227

E. Reynaud, H. Paugam-Moisy

引用次数: 4