发布求助
文献互助 智能选刊 最新文献

VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.最新文献

筛选
英文 中文
Constructive and pruning methods for neural network design 神经网络设计的构造和剪枝方法
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181434
M. Costa, A. Braga, B. R. Menezes
{"title":"Constructive and pruning methods for neural network design","authors":"M. Costa, A. Braga, B. R. Menezes","doi":"10.1109/SBRN.2002.1181434","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181434","url":null,"abstract":"This paper presents methods to improve generalization of multilayer perceptron (MLP) by pruning the original topology without loss in performance. Topology information and validation sets are used. The results show that these techniques are able to choose a minimum network topology and to simplify trained networks.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127317941","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
Control of generalization with a bi-objective sliding mode control algorithm 基于双目标滑模控制算法的泛化控制
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181432
M. Costa, A. Braga, B. R. Menezes, G. G. Parma, R. A. Teixeira
{"title":"Control of generalization with a bi-objective sliding mode control algorithm","authors":"M. Costa, A. Braga, B. R. Menezes, G. G. Parma, R. A. Teixeira","doi":"10.1109/SBRN.2002.1181432","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181432","url":null,"abstract":"This paper presents a new sliding mode control algorithm that is able to guide the trajectory of a multilayer perceptron within the plane formed by the two objectives: training set error and norm of the weight vectors. The results show that the neural networks obtained are able to generate the Pareto set, from which a model with the smallest validation error is selected.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127561337","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
Growing compact RBF networks using a genetic algorithm 使用遗传算法生长紧凑RBF网络
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181436
A. Barreto, H. Barbosa, N. Ebecken
{"title":"Growing compact RBF networks using a genetic algorithm","authors":"A. Barreto, H. Barbosa, N. Ebecken","doi":"10.1109/SBRN.2002.1181436","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181436","url":null,"abstract":"A novel approach for applying genetic algorithms to the configuration of radial basis function networks is presented. A new crossover operator that allows for some control over the competing conventions problem is introduced. Also, a minimalist initialization scheme which tends to generate more parsimonious models is also presented. Finally, a reformulation of generalized cross-validation criterion for model selection, making it more conservative, is discussed. The proposed model is submitted to a computational experiment in order to verify its effectiveness.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126420328","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
Dynamic behaviour forecast as a driving force in the coevolution of one-dimensional cellular automata 动态行为预测作为一维元胞自动机协同进化的驱动力
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181442
G.M.B. Oliveira, Oscar K. N. Asakura, P. D. Oliveira
{"title":"Dynamic behaviour forecast as a driving force in the coevolution of one-dimensional cellular automata","authors":"G.M.B. Oliveira, Oscar K. N. Asakura, P. D. Oliveira","doi":"10.1109/SBRN.2002.1181442","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181442","url":null,"abstract":"Various evolutionary methods have been used to look for cellular automata (CA) with a predefined computational behaviour. The most widely studied CA task is the density classification task (DCT) and the best rule currently known for it was obtained by a coevolutionary genetic algorithm (CGA). Here, we analyse the influence of incorporating a parameter-based heuristic into the coevolutionary search. The results obtained show that the parameters can effectively help a CGA in searching for DCT rules, and suggest that the choice of the amount of bias in the search, allowed for the heuristic, is more sensitive than in previous uses we made of it within standard evolutionary algorithms.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131838420","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
A network of globally coupled chaotic maps for adaptive multi-resolution image segmentation 一种用于自适应多分辨率图像分割的全局耦合混沌映射网络
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181441
Liang Zhao, R. A. Furukawa, A. Carvalho
{"title":"A network of globally coupled chaotic maps for adaptive multi-resolution image segmentation","authors":"Liang Zhao, R. A. Furukawa, A. Carvalho","doi":"10.1109/SBRN.2002.1181441","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181441","url":null,"abstract":"In this paper, a computational model for image segmentation based on a network of coupled chaotic maps is proposed. Time evolutions of chaotic maps that correspond to a pixel class are synchronized with one another, while this synchronized evolution is desynchronized with respect to time evolution of chaotic maps corresponding to other pixel classes in the same data set. The model presents the following advantages in comparison to conventional pixel classification techniques: 1) the segmentation process is intrinsically parallel; 2) the number of pixel classes can be previous unknown; 3) the model offers a multi-resolution and multi-thresholding segmentation approach; 4) the adaptive pixel moving process makes the model robust to classify ambiguous pixels; and 5) the model obtains good performance and transparent dynamics by utilizing one-dimensional chaotic maps instead of complex neurons as individual elements.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133836805","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
Support vector machines with symbolic interpretation 支持向量机与符号解释
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181456
Haydemar Núñez, C. Angulo, Andreu Català
{"title":"Support vector machines with symbolic interpretation","authors":"Haydemar Núñez, C. Angulo, Andreu Català","doi":"10.1109/SBRN.2002.1181456","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181456","url":null,"abstract":"In this work, a procedure for rule extraction from support vector machines (SVMs) is proposed. Our method first determines the prototype vectors by using k-means. Then, these vectors are combined with the support vectors using geometric methods to define ellipsoids in the input space, which are later translated to if-then rules. In this way, it is possible to give an interpretation to the knowledge acquired by the SVM. On the other hand, the extracted rules render possible the integration of SVMs with symbolic AI systems.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116490299","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: 13
An efficient approach of the SOM algorithm to the traveling salesman problem SOM算法求解旅行商问题的一种有效方法
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181459
F. C. Vieira, A. Neto, J. A. F. Costa
{"title":"An efficient approach of the SOM algorithm to the traveling salesman problem","authors":"F. C. Vieira, A. Neto, J. A. F. Costa","doi":"10.1109/SBRN.2002.1181459","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181459","url":null,"abstract":"This paper presents an approach to the well-known traveling salesman problem (TSP) via competitive neural networks. The neural network model adopted in this work is the Kohonen network or self-organizing maps (SOM), which has important topological information about its neurons configuration. This paper is concerned with the initialization aspects, parameters adaptation, and the complexity analysis of the proposed algorithm. The modified SOM algorithm proposed in this paper has shown better results when compared with others neural network based approaches to the TSP.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116633087","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
Forecasting the air transport demand for passengers with neural modelling 基于神经网络模型的航空客运需求预测
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181440
K. Alekseev, J. Seixas
{"title":"Forecasting the air transport demand for passengers with neural modelling","authors":"K. Alekseev, J. Seixas","doi":"10.1109/SBRN.2002.1181440","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181440","url":null,"abstract":"The air transport industry firmly relies on forecasting methods for supporting management decisions. However, optimistic forecasting has resulted in serious problems to the Brazilian industry in the past years. In this paper, models based on artificial neural networks are developed for the air transport passenger demand forecasting. It is found that neural processing can outperform the traditional econometric approach used in this field and can accurately generalise the learning time series behaviour, even in practical conditions, where a small number of data points is available. Feeding the input nodes of the neural estimator with pre-processed data, the forecasting error is evaluated to be smaller than 0.6%.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122127591","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: 22
Neural networks for the analysis of common mental disorders factors 神经网络用于分析常见的精神障碍因素
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181448
C. Lopes, Teresa B Ludermir, M. D. Souto, A. Ludermir
{"title":"Neural networks for the analysis of common mental disorders factors","authors":"C. Lopes, Teresa B Ludermir, M. D. Souto, A. Ludermir","doi":"10.1109/SBRN.2002.1181448","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181448","url":null,"abstract":"The aim of this work is to analyse common mental disorders factors using a multilayer perceptron trained with simulated annealing algorithm. Simulated annealing is used for optimizing both the architecture and weights simultaneously, aiming the identification of the variables which have bigger probability to be related to the problem studied.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130117424","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: 6
Improved generalization learning with sliding mode control and the Levenberg-Marquadt algorithm 利用滑模控制和Levenberg-Marquadt算法改进泛化学习
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181433
M. Costa, A. Braga, B. R. Menezes
{"title":"Improved generalization learning with sliding mode control and the Levenberg-Marquadt algorithm","authors":"M. Costa, A. Braga, B. R. Menezes","doi":"10.1109/SBRN.2002.1181433","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181433","url":null,"abstract":"A variation of the well known Levenberg-Marquardt for training neural networks is presented in this work. The algorithm presented restricts the norm of the weights vector to a preestablished norm value and finds the minimum error solution for that norm value. A range of different norm solutions is generated and the best generalization solution is selected. The results show the efficiency of the algorithm in terms of convergence speed and generalization performance.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130216507","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
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