发布求助
文献互助 智能选刊 最新文献

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

筛选
英文 中文
Detecting rare events with lotto-type competitive learning 利用彩票型竞争学习检测罕见事件
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223959
A. Luk, S. Lien
{"title":"Detecting rare events with lotto-type competitive learning","authors":"A. Luk, S. Lien","doi":"10.1109/IJCNN.2003.1223959","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223959","url":null,"abstract":"This paper highlights the difficulty of detecting small and rare clusters. In theory it is possible for individual neurons, in lotto-type competitive learning algorithms, to follow the source density function. We note that in experiment it is very difficult to locate these small clusters, especially if the prototype set is limited. Two methods are proposed, as exploratory tools, to locate these clusters. The first method is to train the network iteratively with the same prototype set. This simple method enables us to locate these small clusters, albeit with the possibility of over-training. The second method is to deploy supervisory agent(s) to track the trajectory of individual neurons.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"4 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":"130428980","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
SOMICA - an application of self-organizing maps to geometric independent component analysis SOMICA -自组织映射在几何独立分量分析中的应用
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223886
Fabian J Theis, C. Puntonet, E. Lang
{"title":"SOMICA - an application of self-organizing maps to geometric independent component analysis","authors":"Fabian J Theis, C. Puntonet, E. Lang","doi":"10.1109/IJCNN.2003.1223886","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223886","url":null,"abstract":"Guided by the principles of geometric independent component analysis (ICA), we present a new approach (SOM-ICA) to linear geometric ICA using self-organizing map (SOM). We observe a considerable improvement in separation quality of different distributions, albeit at high computational costs. The SOMICA algorithm is therefore primarily interesting from a theoretical point of view bringing together ICA and SOMs; this intersection could lead to new proofs in geometric ICA based on similar theorems in the SOM theory.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"2 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":"134020722","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: 4
Train-spotting: building classifiers for microarrays 列车定位:构建微阵列分类器
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224037
Yuxuan Lan, G. Cawley, R. P. Harvey
{"title":"Train-spotting: building classifiers for microarrays","authors":"Yuxuan Lan, G. Cawley, R. P. Harvey","doi":"10.1109/IJCNN.2003.1224037","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1224037","url":null,"abstract":"The problem of extracting spots from DNA microarrays is a problem of considerable scientific and economic utility. In this paper we introduce a new approach based on a scale-space analysis of the image. We augment this with a machine learning system that guides an operator by classifying spots into those that require further attention and those that are already segmented correctly. We compare conventional k-nearest neighbor techniques with generalized linear models and multilayer perceptrons using confidence intervals and McNemar's test.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"54 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134288589","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
Fusion of structure adaptive self-organizing maps using fuzzy integral 基于模糊积分的结构自适应自组织映射融合
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223264
Kyung-Joong Kim, Sung-Bae Cho
{"title":"Fusion of structure adaptive self-organizing maps using fuzzy integral","authors":"Kyung-Joong Kim, Sung-Bae Cho","doi":"10.1109/IJCNN.2003.1223264","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223264","url":null,"abstract":"Recently, many researchers attempt to develop an effective SOM-based pattern recognizer for high performance classification. Structure adaptive self-organizing map (SASOM) is a variant of SOM that is useful to pattern recognition and visualization. Fusion of classifiers can overcome the limitation of a single classifier by complementing each other. Fuzzy integral is a combination scheme that uses subjectively defined relevance of classifiers. In this paper, fusion of SASOM's using fuzzy integral is proposed for Web mining problem. User profile represents different aspects of user's characteristics and needs an ensemble of classifier that estimate user's preference using Web content labeled by user as \"like\" or \"dislike.\" The proposed method estimates the user profile using subsets of important features extracted from user-rated Web documents. Using UCI Syskill & Webert data, the method is tested and compared with other classifier including ID3, BP and naive Bayes classifier. Experimental results show that the fusion of SASOM's using fuzzy integral can perform better than not only previous studies but also majority voting of SASOM's.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"33 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":"131014120","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
Neuro-hybrid genetic algorithm based economic dispatch for utility system 基于神经混合遗传算法的电力系统经济调度
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223734
N. Kumarappan, M. R. Mohan
{"title":"Neuro-hybrid genetic algorithm based economic dispatch for utility system","authors":"N. Kumarappan, M. R. Mohan","doi":"10.1109/IJCNN.2003.1223734","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223734","url":null,"abstract":"A neuro hybrid Genetic Algorithm (GA) is used to solve an economic dispatch problem. The algorithm has been proposed for minimum cost of operating units. Here Real Coded GA is used for global search and fine tunings are done by Tabu Search (TS) to direct the search towards the optimal region and local optimization. The Fast Decoupled Load Flow (FDLF) is conducted to find the losses by substituting the generation values to the respective PV buses. Then the loss is participated among all generating units using participation factor method. Applying the results again to the load flow checks the voltage limit violation. Artificial Neural Network (ANN) is applied to the Hybrid GA . The algorithm is tested on IEEE 6-bus system and 66-bus utility system. It is observed that the proposed algorithm is optimal, reliable and fast.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"53 75 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":"131155812","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
MMI-based training for a probabilistic neural network 基于mimi的概率神经网络训练
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223987
N. Bu, T. Tsuji, O. Fukuda
{"title":"MMI-based training for a probabilistic neural network","authors":"N. Bu, T. Tsuji, O. Fukuda","doi":"10.1109/IJCNN.2003.1223987","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223987","url":null,"abstract":"Probabilistic neural networks (PNNs) that incorporate the Bayesian decision rule and statistical models have been widely used for pattern classification. Efficient estimation of the PNN's weights, however, is still a major problem. In this paper, we propose a new training scheme based on a discriminative criterion, maximum mutual information (MMI), and apply this method to the log-linearized Gaussian mixture network (LLGMN) which is one of the PNNs. The MMI training achieves a consistent estimator of network weights, and includes the conventional maximum likelihood (ML) algorithm as a special case. Also, the dynamics of terminal attractor (TA) is introduced for iteration control of the MMI training. Finally, the classification ability of the proposed method is examined with a pattern classification problem of the electromyogram (EMG) signals, and found that the MMI training results in better classification than the conventional ML algorithm.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"74 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":"130842327","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
Stability analysis of decentralized motor control 分散电机控制的稳定性分析
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224078
A. Miyamura, K. Aihara
{"title":"Stability analysis of decentralized motor control","authors":"A. Miyamura, K. Aihara","doi":"10.1109/IJCNN.2003.1224078","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1224078","url":null,"abstract":"We consider the decentralized motor control in units of motor units. This idea is motivated by the concept of Sherrington, so that \"our movements are made with various spinal reflexes\", which seems well-suited to the result in physiology and is, in some sense, to the point of understanding the functions or cerebellum motor control. We propose a decentralized version of feedback error learning method and analyze its stability. The efficiency of the proposed algorithm is shown by numerical simulations.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"4 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":"130929023","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
Platform performance comparison of PALM network on Pentium 4 and FPGA PALM网络在Pentium 4和FPGA上的平台性能比较
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223826
Changjian Gao, D. Hammerstrom
{"title":"Platform performance comparison of PALM network on Pentium 4 and FPGA","authors":"Changjian Gao, D. Hammerstrom","doi":"10.1109/IJCNN.2003.1223826","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223826","url":null,"abstract":"When simulating very large, biologically plausible models on desktop computers, the memory bandwidth is the biggest bottleneck due to the significant performance difference between memory and processor. We did a performance analysis for different variations of the Palm association network implemented on Pentium 4 with VTune 6.1 performance analyzer. We also analyzed the performance of an FPGA implementing the same network. The FPGA performance is limited by the memory bandwidth and FPGA computation bandwidth, but continuous sequential memory fetch can be done more efficiently that in the Pentium 4.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"2 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":"130943521","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: 12
Trajectory tracking via adaptive recurrent control with input saturation 基于输入饱和自适应循环控制的轨迹跟踪
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1223372
E. Sánchez, L. J. Ricalde
{"title":"Trajectory tracking via adaptive recurrent control with input saturation","authors":"E. Sánchez, L. J. Ricalde","doi":"10.1109/IJCNN.2003.1223372","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1223372","url":null,"abstract":"This paper deals with the adaptive tracking problem for nonlinear systems in presence of unknown parameters, unmodelled dynamics and input saturation. A high order recurrent neural network is used in order to identify the unknown system and a learning law is obtained using the Lyapunov methodology. Then stabilizing control law for the reference tracking error dynamics is developed using the Lyapunov methodology and the Sontag control law. Tracking error boundedness is established as a function of a design parameter.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"07 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":"131188444","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: 26
Fuzzy Markov predictor in multi-step electric load forecasting 模糊马尔可夫预测器在多步负荷预测中的应用
Proceedings of the International Joint Conference on Neural Networks, 2003. Pub Date : 2003-07-20 DOI: 10.1109/IJCNN.2003.1224061
M. A. Teixeira, Gerson Zaverucha
{"title":"Fuzzy Markov predictor in multi-step electric load forecasting","authors":"M. A. Teixeira, Gerson Zaverucha","doi":"10.1109/IJCNN.2003.1224061","DOIUrl":"https://doi.org/10.1109/IJCNN.2003.1224061","url":null,"abstract":"We present three different approaches for multi-step prediction using the fuzzy Markov predictor (FMP). The FMP is a modification of the hidden Markov model in order to enable it to predict numerical values. In the first approach, the one normally used in neural networks, past predictions are used as input for the next predictions. The second and third approaches follow the standard way of making multi-step prediction in a dynamic Bayesian network. FMP using these three approaches is applied to the task of monthly electric load multi-step forecasting and successfully compared with two Kalman filter models, BATS and STAMP, and two traditional forecasting methods, Box-Jenkins and Winters exponential smoothing.","PeriodicalId":310128,"journal":{"name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","volume":"34 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":"131198249","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: 5
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
小红书