发布求助
文献互助 智能选刊 最新文献

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.最新文献

筛选
英文 中文
Conference topics 会议主题
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2018-09-01 DOI: 10.1109/ijcnn.2005.1555797
{"title":"Conference topics","authors":"","doi":"10.1109/ijcnn.2005.1555797","DOIUrl":"https://doi.org/10.1109/ijcnn.2005.1555797","url":null,"abstract":"","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126847295","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
Dynamic Bayesian networks for machine diagnostics: hierarchical hidden Markov models vs. competitive learning 机器诊断的动态贝叶斯网络:层次隐马尔可夫模型与竞争学习
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556145
F. Camci, R. Chinnam
{"title":"Dynamic Bayesian networks for machine diagnostics: hierarchical hidden Markov models vs. competitive learning","authors":"F. Camci, R. Chinnam","doi":"10.1109/IJCNN.2005.1556145","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556145","url":null,"abstract":"The failure mechanisms of mechanical systems usually involve several degraded health states. Tracking the health state of a machine, even if the machine is working properly, is very critical for detecting, identifying, and localizing the failure (i.e., diagnosis) and estimating the remaining-useful-life of the component/machine (i.e., prognosis) for carrying out proper maintenance. Hidden Markov models (HMM) present us an opportunity to estimate these unobservable health states using observable sensor signals. Hierarchical HMM is composed of sub-HMMs in a hierarchical fashion, providing functionality beyond a HMM for modeling complex systems. Implementation of HMM based models as dynamic Bayesian networks (DBN) facilitates compact representation as well as additional flexibility with regard to model structure. Regular and hierarchical HMMs are employed here to estimate on-line the health state of drill-bits as they deteriorate with use on a CNC drilling machine. In the case of regular HMMs, each HMM (that is part of a committee) competes to represent a distinct health state and learns through competitive learning. In the case of hierarchical HMMs, health states are represented as distinct nodes in the top of the hierarchy. Detailed results from regular and hierarchical HMMs are very promising and are reported in this paper.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115459781","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: 30
Experimental evaluation of a hybrid method for configuring ensemble encoding receptors 一种配置集成编码受体的混合方法的实验评价
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555987
A. M. Abdelbar, D. Hassan, G. Tagliarini, S. Narayan
{"title":"Experimental evaluation of a hybrid method for configuring ensemble encoding receptors","authors":"A. M. Abdelbar, D. Hassan, G. Tagliarini, S. Narayan","doi":"10.1109/IJCNN.2005.1555987","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1555987","url":null,"abstract":"Ensemble encoding is a biologically-motivated, distributed data representation scheme for MLP networks. Multiple overlapping receptive fields are used to enhance the locality of representation. The number, form, and placement of receptive fields has a great impact on performance. In this paper, we explore a technique in which clustering is used to determine receptive field centers, and a variance-based method is used to determine receptive field widths. The relative performance of this hybrid method to other published methods is evaluated experimentally on three benchmark data sets.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115682456","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
Sparse channel estimation with regularization method using convolution inequality for entropy 基于熵卷积不等式的稀疏信道估计正则化方法
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556270
Dongho Han, Sung-Phil Kim, J. Príncipe
{"title":"Sparse channel estimation with regularization method using convolution inequality for entropy","authors":"Dongho Han, Sung-Phil Kim, J. Príncipe","doi":"10.1109/IJCNN.2005.1556270","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556270","url":null,"abstract":"In this paper, we show that the sparse channel estimation problem can be formulated as a regularization problem between mean squared error (MSE) and the L1-norm constraint of the channel impulse response. A simple adaptive method to solve regularization problem using the convolution inequality for entropy is proposed. Performance of this proposed regularization method is compared to the Wiener filter, the matching pursuit (IMP) algorithm and the information criterion based method. The results show that the estimate of the sparse channel using the MSE criterion with the L1-norm constraint outperforms the Wiener filter and the conventional sparse solution methods in terms of MSE of the estimates and the generalization performance.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115719507","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: 10
Dynamical behavior of a chaotic neural and its application to optimization problems 混沌神经系统的动态行为及其在优化问题中的应用
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555946
T. Tanaka, E. Hiura
{"title":"Dynamical behavior of a chaotic neural and its application to optimization problems","authors":"T. Tanaka, E. Hiura","doi":"10.1109/IJCNN.2005.1555946","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1555946","url":null,"abstract":"A model of an analog neuron with chaotic dynamics has been considered, and a chaotic neural network composed of this neuron has also been studied. The chaos neuron model has an internal variable which is evolved by a piecewise sine map, and it shows chaotic behavior. The chaotic neural network is applied to a well-defined optimization problem in order to investigate computational abilities of the present model.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121108545","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
Symbolic rule extraction with a scaled conjugate gradient version of CLARION 符号规则提取与缩放共轭梯度版本的CLARION
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555962
T. Falas, A. Stafylopatis
{"title":"Symbolic rule extraction with a scaled conjugate gradient version of CLARION","authors":"T. Falas, A. Stafylopatis","doi":"10.1109/IJCNN.2005.1555962","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1555962","url":null,"abstract":"This paper presents a hybrid intelligent system made up of two modules. The bottom sub-symbolic module is a multi-layer feed-forward neural network trained by a modified Q-learning methodology that employs the scaled conjugate gradient algorithm. The top module is a symbolic system (implemented with a neural network built on-line) where rules are extracted from the bottom module during training, in a fashion similar to the CLARION system. The two modules augment each other in an effort to obtain a better performance than both of the modules acting alone in solving a problem. The originality of this work lies in the use of the advanced scaled conjugate learning algorithm in such a hybrid system. It is expected that the use of this algorithm would provide significant improvements in the performance of the overall system and also make it less dependent on user-selected parameters. This paper emphasises the implementation details, since the system is currently under development, rather that concrete experimental results.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127088071","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: 3
Rule extraction as a formal method for the verification and validation of neural networks 规则抽取作为一种形式化的方法来验证和验证神经网络
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556388
B. J. Taylor, M.A. Darrah
{"title":"Rule extraction as a formal method for the verification and validation of neural networks","authors":"B. J. Taylor, M.A. Darrah","doi":"10.1109/IJCNN.2005.1556388","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556388","url":null,"abstract":"The term formal method refers to the use of techniques from formal logic and discrete math in the specification, design, and construction of computer systems and software. These techniques enable the formalization of software for development and testing so that it may be verified and validated in a more thorough way. Although not specifically identified in the literature as a verification and validation (V&V) formal method technique, neural network rule extraction fits the basic definition by using techniques from formal logic to formalize neural network software so that it may be examined more completely. This paper identifies several areas where rule extraction can be an effective tool for the V&V of neural networks.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127306340","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: 36
Iterative feature weighting for identification of relevant features with radial basis function networks 基于径向基函数网络的特征迭代加权识别
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556000
B. Duan, Y. Pao
{"title":"Iterative feature weighting for identification of relevant features with radial basis function networks","authors":"B. Duan, Y. Pao","doi":"10.1109/IJCNN.2005.1556000","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556000","url":null,"abstract":"This paper reports on advances in identification of relevant features through iterative feature weighting with radial basis function networks. It proceeds with a set of feature weights to scale the data which are used to train a radial basis function network model. Then from the learned model, the feature weights are updated via one-step gradient descent. The updated feature weights are then fed back to build a new model. The procedure continues until we find a satisfactory model and the feature weights converge. Experimental results for some benchmark datasets show that the approach is efficient and effective for selecting relevant features for data modeling and classification tasks.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127536089","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: 3
An efficient learning algorithm for finding multiple solutions based on fixed-point homotopy method 基于不动点同伦法的高效多解学习算法
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1555985
H. Ninomiya, C. Tomita, H. Asai
{"title":"An efficient learning algorithm for finding multiple solutions based on fixed-point homotopy method","authors":"H. Ninomiya, C. Tomita, H. Asai","doi":"10.1109/IJCNN.2005.1555985","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1555985","url":null,"abstract":"This paper describes an efficient learning algorithm based on fixed-point homotopy method. The proposed algorithm has the ability to train the neural networks with high success rates for the initial guesses compared with other typical second-order training algorithms. Furthermore, the method proposed here not only has the widely convergent property but also find out multiple solutions. The validity of the proposed algorithm for the standard multilayer neural networks is demonstrated through the computer simulations. As a result, it is confirmed that our algorithm is efficient and practical for the learning of the multilayer feedforward neural networks.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126083001","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: 10
Feature selection and condition monitoring of gearbox using SOM 基于SOM的齿轮箱特征选择与状态监测
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI: 10.1109/IJCNN.2005.1556262
G. Liao, T. Shi, Jianping Xuan
{"title":"Feature selection and condition monitoring of gearbox using SOM","authors":"G. Liao, T. Shi, Jianping Xuan","doi":"10.1109/IJCNN.2005.1556262","DOIUrl":"https://doi.org/10.1109/IJCNN.2005.1556262","url":null,"abstract":"Feature selection is a key issue to pattern recognition and condition monitoring. This paper presents an investigation that uses self-organizing maps network to realize feature selection for gearbox condition monitoring. In order to visualize the trained SOM results more clearly, a novel visualization technique is introduced, which can project the high-dimensional input vectors into a 2-dimensional space and prepare a good basis for further analysis. Then with the use of the responses of every dimensional feature in SOM network neurons weights to the input data evaluated according to the Euclidean distances between them, the feature sets being sensitive to pattern recognition are selected. Gearbox vibration signals measured under different operating conditions are analyzed with the method. The results demonstrate that the method selects sensitive feature sets effectively and has a good potential for gearbox condition monitoring in practice.","PeriodicalId":365690,"journal":{"name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123232819","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: 1
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信