发布求助
文献互助 智能选刊 最新文献

2007 International Joint Conference on Neural Networks最新文献

筛选
英文 中文
An Attention Selection Model with Visual Memory and Online Learning 视觉记忆与在线学习的注意选择模型
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4371145
Chenlei Guo, Liming Zhang
{"title":"An Attention Selection Model with Visual Memory and Online Learning","authors":"Chenlei Guo, Liming Zhang","doi":"10.1109/IJCNN.2007.4371145","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4371145","url":null,"abstract":"In this paper, an attention selection model with visual memory and online learning is proposed, which has three parts: Sensory Mapping (SM), Cognitive Mapping (CM) and Motor Mapping (MM). CM is the novelty of our model which incorporates visual memory and online learning. In order to mimic visual memory, we put forward an Amnesic Incremental Hierachical Discriminant Regression (AIHDR) Tree which has an amnesic function to guide the deletion of redundant information of the tree. Experimental results show that our AIHDR tree has better performance in retrieval speed and accuracy than IHDR/HDR tree. Self-Supervised Competition Neural Network (SSCNN) in CM has the characteristics of online learning since its connection weights can be updated in real time according to the change of environment. Eyeball Movement Prediction (EMP) mechanism is applied to estimate the movement of human eyeball so that attention can be focused on interested objects. Several applications such as object tracking and robot self-localization are realized by our proposed work.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125794535","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
Neural Networks Applied to Adjustment and Combination of the Control Actions for the Cold Rolling Process 神经网络在冷轧过程控制动作调整与组合中的应用
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4371034
Luis E. Zárate, F. R. Bittencout
{"title":"Neural Networks Applied to Adjustment and Combination of the Control Actions for the Cold Rolling Process","authors":"Luis E. Zárate, F. R. Bittencout","doi":"10.1109/IJCNN.2007.4371034","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4371034","url":null,"abstract":"The cold rolling process involves several parameters as back and front tensions, friction coefficient, among others. Any alteration in any of them will affect the output thickness of the strip being rolled. Each operation region demands a different control action. The action can be through gap, back or front tensions or, more effectively, through the combination of them. The metallurgical industry is still dependent on the operator skill, whose actions can act on several control parameters, but not simultaneously. In this work, a technique to choose the combination of the most adequate control action is presented. The technique uses a neural representation, the operator background and also the sensitivity equations of the process, obtained through the differentiation of the previously trained neural network. The expert knowledge about the choice of the control actions combined is represented through a matrix, using the concepts of fuzzy sets.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125967593","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
Fast Learning Artificial Neural Network (FLANN) Based Color Image Segmentation in R-G-B-S-V Cluster Space 基于快速学习人工神经网络(FLANN)的R-G-B-S-V聚类空间彩色图像分割
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4371018
Xuejie Zhang, A. Tay
{"title":"Fast Learning Artificial Neural Network (FLANN) Based Color Image Segmentation in R-G-B-S-V Cluster Space","authors":"Xuejie Zhang, A. Tay","doi":"10.1109/IJCNN.2007.4371018","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4371018","url":null,"abstract":"In a previous paper, we introduced a biologically inspired binocular vision system, the CogV, that exhibits partial characteristics of human vision and attention. To further the work, the investigation focused onto partitioning the image space into regions of interests that may simulate exogenous attention. The first step for human to perceive an environment is through a series of attention cues that may summon portions of edges, regions, colors, and prevailing thoughts in order to understand the prevailing environment. Through this process, the brain then decides to focus on some region to extract further information from it. This paper proposes a fast color image segmentation algorithm which may be used for vision applications. This approach is based on Fast Learning Artificial Neural Networks (FLANN) clustering and segmentation based on coherence between neighboring pixels. The proposed segmentation algorithm has been incorporated into the existing CogV system as a simplified model that we relate loosely to the superior colliculus (SC). The purpose of this module is to gain an initial overall perception of the environment and highlight regions of interest that the perceptual system may concern itself with. In the process, the SC provides a means to detect exogenous stimuli and thus reducing the initial search domain for object positions.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126196353","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: 21
Search Strategies Guided by the Evidence for the Selection of Basis Functions in Regression 基于证据的回归基函数选择搜索策略
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4370996
Ignacio Barrio, E. Romero, L. B. Muñoz
{"title":"Search Strategies Guided by the Evidence for the Selection of Basis Functions in Regression","authors":"Ignacio Barrio, E. Romero, L. B. Muñoz","doi":"10.1109/IJCNN.2007.4370996","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4370996","url":null,"abstract":"This work addresses the problem of selecting a subset of basis functions for a model linear in the parameters for regression tasks. Basis functions from a set of candidates are explicitly selected with search methods coming from the feature selection field. Following approximate Bayesian inference, the search is guided by the evidence. The tradeoff between model complexity and computational cost can be controlled by choosing the search strategy. The experimental results show that, under mild assumptions, compact and very competitive models are usually found.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124822596","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
Application of Neural Networks to the Electroencephalogram Analysis for Epilepsy Detection 神经网络在癫痫检测脑电图分析中的应用
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4371386
V. Golovko, Svetlana V. Bezobrazova, Sergei V. Bezobrazov, U. Rubanau
{"title":"Application of Neural Networks to the Electroencephalogram Analysis for Epilepsy Detection","authors":"V. Golovko, Svetlana V. Bezobrazova, Sergei V. Bezobrazov, U. Rubanau","doi":"10.1109/IJCNN.2007.4371386","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4371386","url":null,"abstract":"Many techniques were used in order to detect and to predict epileptic seizures on the basis of electroencephalograms. One of the approaches for the prediction of the epileptic seizures is the use the chaos theory, namely determination largest Lyapunov's exponent or correlation dimension of the scalp EEG signals. This paper presents the neural network technique for epilepsy detection. It is based on computing of the largest Lyapunov's exponent. The results of experiments are discussed.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128313164","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
An Artificial Neural Networks Based Dynamic Decision Model for Time-Series Forecasting 基于人工神经网络的时间序列预测动态决策模型
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4371041
Yuehui Chen, F. Chen, Qiang Wu
{"title":"An Artificial Neural Networks Based Dynamic Decision Model for Time-Series Forecasting","authors":"Yuehui Chen, F. Chen, Qiang Wu","doi":"10.1109/IJCNN.2007.4371041","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4371041","url":null,"abstract":"The forecasting models for time series forecasting using computational intelligence such as artificial neural networks (ANNs) , genetic programming (GP) and gene expression programming (GEP), especially hybrid particle swarm optimization (PSO) algorithm and artificial neural networks (ANNs) have achieved favorable results. However, these studies, have assumed a static environment. This paper investigates the development of a new dynamic decision forecasting model. The input size of the ANNs will be dynamical changed in the process of evolution. Application results prove the higher precision and generalization capacity obtained by this new method than the static models.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128376880","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
Learning Long-Term Time Series with Generative Topographic Mapping 用生成式地形映射学习长期时间序列
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4370947
Feng Zhang
{"title":"Learning Long-Term Time Series with Generative Topographic Mapping","authors":"Feng Zhang","doi":"10.1109/IJCNN.2007.4370947","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4370947","url":null,"abstract":"We propose a generative topographic mapping (GTM) based nonlinear model for long-term time series prediction. As a modification of Kohonen self-organizing maps (SOM), GTM has been applied to data classification, visualization and other machine learning problems, however, limited research have been proposed in time series analysis. With a double application of GTM algorithm, a specially designed approach can quantize input data to store temporal evolvement information for trend prediction. Experimental results demonstrate the improved forecast accuracy in long-term trend learning.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129640146","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
Application of Self-Organizing Map in Aerosol Single Particles Data Clustering 自组织映射在气溶胶单粒子数据聚类中的应用
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4371093
Guo-Zhu Wen, Xiaolian Guo, De-shuang Huang, KunHong Liu
{"title":"Application of Self-Organizing Map in Aerosol Single Particles Data Clustering","authors":"Guo-Zhu Wen, Xiaolian Guo, De-shuang Huang, KunHong Liu","doi":"10.1109/IJCNN.2007.4371093","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4371093","url":null,"abstract":"In this paper, self-organizing map (SOM) is used to visualize and cluster the data set of aerosol single particle mass spectrum, which was collected by aerosol time-of-flight mass spectrometry (ATOFMS). In view of the characteristic feature of aerosol particle data, the TF-IDF scheme used widely in document clustering is employed to preprocess. Subsequently for data clustering analysis, a two-level clustering framework is proposed, wherein SOM is firstly used to cluster input data and get the primary results, and then the results are again clustered by semiautomatic k-means algorithm. In order to demonstrate the validity of clustering, the chemical significance for cluster centroid is also investigated, wherein inorganic salts, \"calcium-containing\" particles, biogenic soot particles, and carbonaceous particles etc. are identified.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127212567","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: 2
Face Localization In Color Images Using Dynamic Time Warping And Integral Projections 基于动态时间扭曲和积分投影的彩色图像人脸定位
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4371076
L. M. Lopez, R. P. Elias, Jonathan Villanueva Tavira
{"title":"Face Localization In Color Images Using Dynamic Time Warping And Integral Projections","authors":"L. M. Lopez, R. P. Elias, Jonathan Villanueva Tavira","doi":"10.1109/IJCNN.2007.4371076","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4371076","url":null,"abstract":"The face localization and the facial features extraction have received a great attention in the context of the human-computer interaction. In this paper a method for face localization is described. This method locate human faces in color scenes with some variations in the illumination and pose. The first task is segment the image in areas with skin color, the biggest area is selected, then the integral projections are extracted at this area; dynamic time warping is used to align these integral projections with some templates. The templates are created from an average face which was extracted of a set of images that contain just a face. If the alignment is good the area is declared a true face.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127343842","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
Eigenvalue Analysis on Singularity in RBF networks RBF网络奇异性的特征值分析
2007 International Joint Conference on Neural Networks Pub Date : 2007-10-29 DOI: 10.1109/IJCNN.2007.4371040
Haikun Wei, S. Amari
{"title":"Eigenvalue Analysis on Singularity in RBF networks","authors":"Haikun Wei, S. Amari","doi":"10.1109/IJCNN.2007.4371040","DOIUrl":"https://doi.org/10.1109/IJCNN.2007.4371040","url":null,"abstract":"It has long been observed that strange behaviors happen in the gradient learning process of neural networks including multilayer perceptrons (MLPs) and RBF networks because of the singularities arisen from the symmetric structure in these models. The learning behaviors nearby are crucially dependant on the stability of the singularity. For RBF networks, this paper analyzes the stability by investigating the eigenvalues of the Hessian matrix on the overlap singularities. We show that the overlap singularity is a partially stable critical line, and there is only one nonzero eigenvalue on the singularity. The influence of the teacher parameters and initial conditions on eigenvalues is also discussed.","PeriodicalId":350091,"journal":{"name":"2007 International Joint Conference on Neural Networks","volume":"2011 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127369190","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
首页 上一页 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：604180095
Book学术官方微信