Proceedings of the International Joint Conference on Neural Networks, 2003.最新文献

筛选
英文 中文
Neural networks for web page classification based on augmented PCA 基于增强主成分分析的网页分类神经网络
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223679
A. Selamat, S. Omatu
{"title":"Neural networks for web page classification based on augmented PCA","authors":"A. Selamat, S. Omatu","doi":"10.1109/IJCNN.2003.1223679","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223679","url":null,"abstract":"Automatic categorization is the only viable method to deal with the scaling problem of the World Wide Web (WWW). In this paper, we propose a news web page classification method (WPCM). The WPCM uses a neural network with inputs obtained by both the principal components and class profile-based features (CPBF). Each news web page is represented by the term-weighting scheme. As the number of unique words in the collection set is big, the principal component analysis (PCA) has been used to select the most relevant features for the classification. Then the final output of the PCA is augmented with the feature vectors from the class-profile which contains the most regular words in each class before feeding them to the neural networks. We have manually selected the most regular words that exist in each class and weighted them using an entropy weighting scheme. The fixed number of regular words from each class will be used as a feature vectors together with the reduced principal components from the PCA. These feature vectors are then used as the input to the neural networks for classification. The experimental evaluation demonstrates that the WPCM method provides acceptable classification accuracy with the sports news datasets.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"221 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":"123233390","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: 18
Annealed imitation: fast dynamics for maximum clique 退火模拟:快速动态最大的集团
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223289
M. Pelillo
{"title":"Annealed imitation: fast dynamics for maximum clique","authors":"M. Pelillo","doi":"10.1109/IJCNN.2003.1223289","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223289","url":null,"abstract":"We propose a new class of heuristics for the maximum clique problem (MCP) whose basic ingredients are: (1) a parameterized continuous formulation of MCP, (2) an instability analysis of equilibria of imitation dynamics from evolutionary game theory, and (3) a principled way of varying a regularization parameter during the evolution process so as to avoid inefficient solutions. The resulting annealed imitation\" class is shown to contain algorithms that are dramatically faster than and as accurate as state-of-the-art neural network heuristics for maximum clique.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"25 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":"126336862","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
Classification of eukaryotic and prokaryotic cells by a backpropagation network 真核和原核细胞的反向传播网络分类
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223666
T. Kristensen, R. Patel
{"title":"Classification of eukaryotic and prokaryotic cells by a backpropagation network","authors":"T. Kristensen, R. Patel","doi":"10.1109/IJCNN.2003.1223666","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223666","url":null,"abstract":"In this paper we show how a Backpropagation neural network is used to classify between eukaryotic and prokaryotic cells. The classification is based on their DNA (Deoxyribonuclei) sequences which are obtained from different databases available on the Internet. The sequences are first preprocessed using a sliding window technique to obtain sub-sequence frequencies, and then normalised to make them comparable.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"136 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":"121342324","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: 7
Threshold-based dynamic annealing for multi-thread DAEM and its extreme 基于阈值的多线程DAEM动态退火及其极限
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223397
M. Takada, R. Nakano
{"title":"Threshold-based dynamic annealing for multi-thread DAEM and its extreme","authors":"M. Takada, R. Nakano","doi":"10.1109/IJCNN.2003.1223397","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223397","url":null,"abstract":"The EM algorithm is an efficient algorithm to obtain the ML estimate for incomplete data, but has the local optimality problem. The deterministic annealing EM (DAEM) algorithm was once proposed to solve the problem, but it not guaranteed to obtain the global optimum since it employs a single token search. Then multi-thread DAEM (m-DAEM) algorithm was proposed by incorporating a search framework of multiple tokens, giving further improvement of solution quality with a heavy computing cost. This paper proposes another variant of m-DAEM, called /spl epsiv/-DAEM, by introducing threshold-based dynamic annealing where the Hessian information is made good use of. Given the adequate /spl epsiv/, the /spl epsiv/-DAEM shows excellent performance. Moreover, its extreme case where /spl epsiv/ /spl rarr/ /spl infin/, called the multi-thread EM, also shows rather excellent performance.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"192 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":"114069815","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: 7
Supervised synaptic weight adaptation for a spiking neuron 脉冲神经元的监督突触权重适应
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223968
B. Davis, Deniz Erdoğmuş, Y. Rao, J. Príncipe
{"title":"Supervised synaptic weight adaptation for a spiking neuron","authors":"B. Davis, Deniz Erdoğmuş, Y. Rao, J. Príncipe","doi":"10.1109/IJCNN.2003.1223968","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223968","url":null,"abstract":"A novel algorithm named Spike-LMS is described that adapts the synaptic weights of an artificial spiking neuron to produce a desired response. The derivation of Spike-LMS follows from the derivation of the least-mean squares (LMS) algorithm used in adaptive filter theory. Spike-LMS works directly in the domain of spike trains, and therefore makes no assumptions about any particular neural encoding method. This algorithm is able to identify the synaptic weights of a spiking neuron given the pre-synaptic and post-synaptic spike trains.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"12 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":"116070195","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
Multi-objective optimal control of batch processes using recurrent neuro-fuzzy networks 基于递归神经模糊网络的批处理多目标最优控制
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223362
Jie Zhang
{"title":"Multi-objective optimal control of batch processes using recurrent neuro-fuzzy networks","authors":"Jie Zhang","doi":"10.1109/IJCNN.2003.1223362","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223362","url":null,"abstract":"A recurrent neuro-fuzzy network based strategy for batch process modelling and multi-objective optimal control is presented. In this recurrent neuro-fuzzy network a \"global\" nonlinear long-range prediction model is constructed from the fuzzy conjunction of a number of \"local\" linear dynamic models. The network output is fed back to the network input through one or more time delay units. This particular structure ensures that predictions from a recurrent neuro-fuzzy network are long-range or multi-step-ahead predictions. Process knowledge is used to initially partition the process nonlinear characteristics into several local operating regions and to aid in the initialisation of the corresponding network weights. Process input output data is then used to train the network. Membership functions of the local regimes are identified and local models are discovered through network training. In this paper, a recurrent neuro-fuzzy network is used to model a fed-batch reactor and to calculate the optimal feeding policy.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"11 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":"123825402","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: 7
Dynamic cortical cooperation related to visual perception 与视觉知觉有关的动态皮层合作
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223931
R. Eckhorn, A. Gail, A. Bruns, B. Al-Shaikhli
{"title":"Dynamic cortical cooperation related to visual perception","authors":"R. Eckhorn, A. Gail, A. Bruns, B. Al-Shaikhli","doi":"10.1109/IJCNN.2003.1223931","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223931","url":null,"abstract":"We have continued testing the hypothesis of visual feature-binding by synchronization in/spl gamma/ monkey visual cortex. Current support for this hypothesis comes from recent results demonstrating local synchrony among rhythmic or stochastic /spl gamma/-activities (30-90Hz) - including their perceptual modulation - and decoupling of /spl gamma/-activity among neural groups representing figure and background. On the other hand, /spl gamma/-synchrony in primary visual cortex is restricted to few millimeters, which challenges the binding-by-synchronization hypothesis for larger cortical distances. But we found that this restriction is due to extended traveling /spl gamma/-waves, randomly altering their directions. Thus, across intermediate distances, phase continuity of these waves may still support coding of object continuity. Finally, across large distances we observed cortico-cortical interactions among low frequency signals and the envelopes of amplitude-modulated /spl gamma/-signals. We discuss potential mechanisms of near-, medium- and far-range cooperativity on the basis of spike-coding model networks. They include two types of inhibitory feedback loops generating local /spl gamma/-activities and low-frequency modulations, respectively. In conclusion, we propose that the binding-by-synchronization hypothesis, initially restricted to synchrony of oscillatory /spl gamma/-signals, be extended to more general forms of signal coupling, including near-range phase synchrony (coherence) between /spl gamma/-activities, medium-range phase continuity of /spl gamma/-waves, and far-range coupling involving low-frequency signals and envelopes of /spl gamma/-signals.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"45 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":"121601640","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
Real-time image transmission on the TCP/IP network using wavelet transform and neural network 利用小波变换和神经网络实现TCP/IP网络上的实时图像传输
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223865
J. Kim, H. Kim, B. Nam
{"title":"Real-time image transmission on the TCP/IP network using wavelet transform and neural network","authors":"J. Kim, H. Kim, B. Nam","doi":"10.1109/IJCNN.2003.1223865","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223865","url":null,"abstract":"In this paper we discuss an algorithm for real time transmission of moving color images on the TCP/IP network using wavelet transform and neural network. The image frames received from the camera are two-level wavelet transformed in the server, and are transmitted to the client on the network. Then, the client performs the inverse wavelet-transform using only the received pieces of each image frame within the prescribed time limit to display the moving images. When the TCP/IP network is busy, only a fraction of each image frame is delivered. When the line is free, the whole frame of each image is transferred to the client. The receiver warns the sender of the condition of traffic congestion in the network by sending a special short frame for this specific purpose. The sender can respond to this information of warning by simply reducing the data rate which is adjusted by a back-propagation neural network. In this way we can send a stream of moving images by adaptively adjusting to the network traffic condition.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"7 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":"125283086","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
A two-processing element adaptable linear oscillating recurrent system with single-weight plasticity 具有单重塑性的双加工单元自适应线性振荡循环系统
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223286
M. Johnson, J. Príncipe
{"title":"A two-processing element adaptable linear oscillating recurrent system with single-weight plasticity","authors":"M. Johnson, J. Príncipe","doi":"10.1109/IJCNN.2003.1223286","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223286","url":null,"abstract":"A simple recursive linear two-processing element adaptable oscillator is developed and demonstrated. Simple harmonic motion and its mathematical description is the foundation of this study. State equations for an undamped spring-mass system are converted to a discrete time system, followed by eigenvalue analysis to convert the four-degree-of-freedom system to a recursive network with plasticity in one variable. The oscillator is initialized to a frequency in the neighborhood of the desired frequency, and tuned by using resilient backpropagation modified for backpropagation through time. It is shown that the network can track frequencies in a spectrum of operation as defined by the sampling frequency, given the network is initialized to frequencies in the neighborhood of those of interest.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"222 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":"122401377","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
Modular adaptive RBF-type neural networks for letter recognition 字母识别的模块化自适应rbf型神经网络
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223416
G. Daqi, Li Chengyin, Li Changwu
{"title":"Modular adaptive RBF-type neural networks for letter recognition","authors":"G. Daqi, Li Chengyin, Li Changwu","doi":"10.1109/IJCNN.2003.1223416","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223416","url":null,"abstract":"This paper proposes a modular RBF-type network classifier consisting of multiple single-layer RBF networks and perceptrons for solving large-sample and high-dimensional classification problems. The method for optimally determining the number, locations and widths of RBF kernels and the target values of Gaussian activation functions is gone into details. The presented method, which only propagates errors one layer backwards, has much lower computational complexity than the backpropogation algorithm used in multilayer feedforward perceptrons and RBF networks. The result for letter recognition shows that modular RBF-type network classifiers as well as the adaptively learning algorithm have faster convergence rate, higher classification accuracy, larger probability to get optimal structures, and better performance to reach global minimum points, compared with the standard RBF networks and multilayer feedforward perceptrons.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"5 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":"131273442","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
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
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
小红书