Proceedings of the International Joint Conference on Neural Networks, 2003.最新文献_第8页

Diagnostic monitoring of internal combustion engines by use of independent component analysis and neural networks 利用独立成分分析和神经网络对内燃机进行诊断监测

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223804

J. P. Barnard, C. Aldrich

引用次数: 7

Human head detection using multi-modal object features 基于多模态目标特征的人体头部检测

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223738

Yun Luo, Y. Murphey, F. Khairallah

引用次数: 6

Comparison of L1 and L2 support vector machines L1和L2支持向量机的比较

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223724

Y. Koshiba, S. Abe

引用次数: 21

A hybrid dynamical system as an automaton on the fractal set 分形集上作为自动机的混合动力系统

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223796

J. Nishikawa, K. Gohara

{"title":"A hybrid dynamical system as an automaton on the fractal set","authors":"J. Nishikawa, K. Gohara","doi":"10.1109/IJCNN.2003.1223796","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223796","url":null,"abstract":"It is well known that a brain consists of many sub-modules, each of which performs a specific role. The experimental results many studies have indicated that prefrontal cortex appropriately switches each module. In this paper, we consider the brain as a hybrid dynamical system, which is composed of a higher module having discrete dynamics and a lower module having continuous dynamics. Two typical systems are investigated from the viewpoint of dynamical systems. When the higher module stochastically switches inputs to the lower module, i.e., a non-feedback system, the dynamics is characterizes by an attractive and invariant fractal set having hierarchical clusters addressed by input sequences. When the higher module switches according to the state of the lower module, i.e., a feedback system, various switching attractors correspond to infinite switching manifolds, which define each feedback control rule at the switching point. The switching attractors in the feedback system are the subsets of the fractal set in the non-feedback system. The system can be considered an automaton, which generated various sequences from the fractal, set by choosing the typical switching manifold.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"6 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":"130863004","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

Explaining how a multi-layer perceptron predicts helicopter airframe load spectra from continuously valued flight parameter data 解释多层感知器如何从连续飞行参数数据中预测直升机机体载荷谱

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223837

M. Vaughn, J.G. Franks

引用次数: 0

Incorporating invariants in Mahalanobis distance based classifiers: application to face recognition 结合马氏距离分类器的不变量:在人脸识别中的应用

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224070

A. Fraser, N. Hengartner, K. Vixie, B. Wohlberg

{"title":"Incorporating invariants in Mahalanobis distance based classifiers: application to face recognition","authors":"A. Fraser, N. Hengartner, K. Vixie, B. Wohlberg","doi":"10.1109/IJCNN.2003.1224070","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1224070","url":null,"abstract":"We present a technique for combining prior knowledge about transformations that should be ignored with a covariance matrix estimated from training data to make an improved Mahalanobis distance classifier. Modern classification problems often involve objects represented by high-dimensional vectors or images (for example, sampled speech or human faces). The complex statistical structure of these representations is often difficult to infer from the relatively limited training data sets that are available in practice. Thus, we wish to efficiently utilize any available a priori information, such as transformations or the representations with respect to which the associated objects are known to retain the same classification (for example, spatial shifts of an image of a handwritten digit do not alter the identity of the digit). These transformations, which are often relatively simple in the space of the underlying objects, are usually nonlinear in the space of the object representation, making their inclusion within the framework of a standard statistical classifier difficult. Motivated by prior work of Simard et al. (1998; 2000), we have constructed a new classifier which combines statistical information from training data and linear approximations to known invariance transformations. When tested on a face recognition task, performance was found to exceed by a significant margin that of the best algorithm in a reference software distribution.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"1 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":"130942950","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: 20

Hierarchical and dynamic SOM applied to image compression 分层动态SOM在图像压缩中的应用

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223472

J.M. Barbalho, J.A.F. Costa, A. Neto, M. Netto

引用次数: 3

Architecture research and hardware implementation on simplified neural computing system for face identification 人脸识别简化神经计算系统的体系结构研究与硬件实现

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223818

Xu Jian, Weijun Li, Qu Yanfeng, Qin Hong, Wang Shoujue

引用次数: 4

Three improved fuzzy lattice neurocomputing (FLN) classifiers 三种改进的模糊格神经计算(FLN)分类器

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223707

A. Cripps, N. Nguyen, V. Kaburlasos

引用次数: 8

An analog neural oscillator circuit for locomotion controller in quadruped walking robot 四足步行机器人运动控制器模拟神经振荡器电路

Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223824

K. Nakada, T. Asai, Y. Amemiya

引用次数: 9