发布求助
文献互助 智能选刊 最新文献

Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks最新文献

筛选
英文 中文
Neuro-fuzzy networks for pattern classification and rule extraction 用于模式分类和规则提取的神经模糊网络
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889761
G. Conde, Patrícia G. Ramos, G. C. Vasconcelos
{"title":"Neuro-fuzzy networks for pattern classification and rule extraction","authors":"G. Conde, Patrícia G. Ramos, G. C. Vasconcelos","doi":"10.1109/SBRN.2000.889761","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889761","url":null,"abstract":"Summary form only given. An experimental evaluation of the neurofuzzy models NEFCLASS and FuNN is conducted in real world pattern recognition applications. The models are investigated with respect to classification performance and the number of rules generated and compared to the traditional MLP network trained with backpropagation. The models NEFCLASS and FuNN are examined in benchmarking problems from the Proben1 database and in a large-scale credit card screening problem. A comparison is established with an MLP network and the results obtained show some potential advantages of the neuro-fuzzy classifiers over the MLP particularly with respect to the ability of the neuro-fuzzy models to generate a knowledge base of rules.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123168009","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
Mental imagery in explanations of visual object classification 视觉对象分类解释中的心理意象
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889728
E. Burattini, M. D. Gregorio, G. Tamburrini
{"title":"Mental imagery in explanations of visual object classification","authors":"E. Burattini, M. D. Gregorio, G. Tamburrini","doi":"10.1109/SBRN.2000.889728","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889728","url":null,"abstract":"This paper investigates the integration of verbal and visual information in explanation, from a hybrid neuro-symbolic perspective. The effectiveness of explanations provided by human experts is known to be often enhanced by multiple representation techniques. The latter seem particularly suitable in explanations concerning high-level visual tasks involving both top-down reasoning and bottom-up perceptual processes.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132615235","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
Using the GasNet model in discrete domains 在离散域中使用GasNet模型
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889744
Carmen L. R. Santos, Celso R. Souza, P. D. Oliveira, P. Husbands
{"title":"Using the GasNet model in discrete domains","authors":"Carmen L. R. Santos, Celso R. Souza, P. D. Oliveira, P. Husbands","doi":"10.1109/SBRN.2000.889744","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889744","url":null,"abstract":"A neural network model-the GasNet-has been reported in the literature, which, in addition to the traditional electric type, point-to-point communication between units, also uses communication through a diffusable chemical modulator. Here we assess the applicability of this model in two different scenarios, the XOR problem and a simulated food gathering task. Both represent simpler and more discrete domains than the one in which GasNet was originally introduced (which had an essentially continuous nature), thus allowing for distinct issues to be addressed; also, both are well-known benchmark problems from the literature. The experiments were intended to better understand the model from analogies with traditional architectures as well as to extend the original problem domain, comparing its performance with some of the ones previously presented.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116335229","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
Evolutionary optimization of RBF networks RBF网络的进化优化
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889742
E. D. Lacerda, Teresa B Ludermir, A. Carvalho
{"title":"Evolutionary optimization of RBF networks","authors":"E. D. Lacerda, Teresa B Ludermir, A. Carvalho","doi":"10.1109/SBRN.2000.889742","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889742","url":null,"abstract":"One of the main obstacles to the widespread use of artificial neural networks is the difficulty of adequately defining values for their free parameters. The article discusses how radial basis function (RBF) networks can have their parameters defined by genetic algorithms. For such, it presents an overall view of the problems involved and the different approaches used to genetically optimize RBF networks. Finally, a model is proposed which includes representation, crossover operator and multiobjective optimization criteria. Experimental results using this model are presented.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"14 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115590904","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: 33
Web text mining using a hybrid system 使用混合系统的Web文本挖掘
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889727
F. H. Fukuda, L. Neto, V. D. R. Junior, E. Antonio, L. Chiganer, Emmanuel L. P. Passos, M. Pacheco, J. Valério
{"title":"Web text mining using a hybrid system","authors":"F. H. Fukuda, L. Neto, V. D. R. Junior, E. Antonio, L. Chiganer, Emmanuel L. P. Passos, M. Pacheco, J. Valério","doi":"10.1109/SBRN.2000.889727","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889727","url":null,"abstract":"This paper presents the research of artificial intelligence techniques based on knowledge discovery in databases (KDD), knowledge discovery in texts, expert systems and artificial neural networks (ANN) applied for evaluation and selection of textual documents found on the World Wide Web. These techniques are useful because nowadays we have a explosive growth of the Web that provides a great amount of documents of many different subjects and the user needs to select these documents regarding to theirs particular interests. We considered the Web as a large data warehouse and applied the KDD fundament and text mining procedures to develop these techniques. The techniques developed are language syntax independent because they do not use the NLP parser and provide an automatic text evaluation based on user profile interests acquired by examples using ANN. Finally, we developed a system using these techniques and compared with a similar commercial system available in the Web.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129399148","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
A multi-objective optimization approach for training artificial neural networks 人工神经网络训练的多目标优化方法
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889733
R. A. Teixeira, A. Braga, R. Takahashi, R. R. Saldanha
{"title":"A multi-objective optimization approach for training artificial neural networks","authors":"R. A. Teixeira, A. Braga, R. Takahashi, R. R. Saldanha","doi":"10.1109/SBRN.2000.889733","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889733","url":null,"abstract":"Presents a learning scheme for training multilayer perceptrons (MLPs) with improved generalization ability. The algorithm employs a training algorithm based on a multi-objective optimization mechanism. This approach allows balancing between the training squared error and the norm of the network weight vector. This balancing is correlated with the trade-off between overfitting and underfitting. The method is applied to classification and regression problems and also compared with weight decay, support vector machines and standard backpropagation results. The proposed method leads to training results that are the best ones, and additionally allows a systematic procedure for training neural networks, with less heuristic parameter adjustments than the other methods.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130377668","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
An efficient implementation of a learning method for Mamdani fuzzy models Mamdani模糊模型学习方法的有效实现
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889710
L. Schnitman, T. Yoneyama
{"title":"An efficient implementation of a learning method for Mamdani fuzzy models","authors":"L. Schnitman, T. Yoneyama","doi":"10.1109/SBRN.2000.889710","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889710","url":null,"abstract":"This paper presents an efficient implementation of a supervised learning method based on membership function training in the context of Mamdani fuzzy models. The main idea is to adjust the antecedent and consequent membership functions that are of asymmetric trapezoidal form by backpropagating the output error through the fuzzy net. The proposed implementation is analogous to the training scheme commonly used with Takagi-Sugeno fuzzy models but it requires additional procedures that are related to some specific characteristics of the Mamdani fuzzy structures. Some numerical results are provided as illustrations.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117046151","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
Design of a fuzzy controller with simplified architecture 一种结构简化的模糊控制器设计
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889716
M. E. Bordon, I. Silva, A. Souza
{"title":"Design of a fuzzy controller with simplified architecture","authors":"M. E. Bordon, I. Silva, A. Souza","doi":"10.1109/SBRN.2000.889716","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889716","url":null,"abstract":"This work presents the design of a fuzzy controller with simplified architecture. This architecture tries to minimize the time processing used in the several stages of hazy modeling of systems and processes. The basic procedures of fuzzification and defuzzification are simplified to the maximum while the inference procedures are computed in private way. Therefore, the simplified architecture allows a fast and easy configuration of the fuzzy controller. All rules that define the control actions are determined by inference procedures and the defuzzification is made automatically using a simplified algorithm. The fuzzy controller operation is standardized and the control actions are previously calculated. For general-purpose application and results, the industrial systems of fluid flow control will be considered.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"180 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114117585","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
A hierarchical neural model in short-term load forecasting 短期负荷预测中的层次神经网络模型
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889725
O. Carpinteiro, Agnaldo J. R. Reis, A. P. D. Silva
{"title":"A hierarchical neural model in short-term load forecasting","authors":"O. Carpinteiro, Agnaldo J. R. Reis, A. P. D. Silva","doi":"10.1109/SBRN.2000.889725","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889725","url":null,"abstract":"This paper proposes a novel neural model for the short-term load forecasting problem. The neural model is made up of two self-organizing map nets-one on top of the other. It has been successfully applied to domains in which the context information given by former events plays a primary role. The model was trained and assessed on the load data extracted from a Brazilian electric utility. It was required to predict once every hour the electric load during the next 24 hours. The paper presents the results and evaluates them.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126164065","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: 87
Monthly stream flow forecasting using an neural fuzzy network model 利用神经模糊网络模型进行月流量预测
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889724
M. Valença, Teresa B Ludermir
{"title":"Monthly stream flow forecasting using an neural fuzzy network model","authors":"M. Valença, Teresa B Ludermir","doi":"10.1109/SBRN.2000.889724","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889724","url":null,"abstract":"This paper presents an fuzzy neural network model for inflow forecast for the Sobradinho hydroelectric power plant, part of the Chesf (Companhia Hidreletrica do Sao Francisco-Brazil) system. The model was implemented to forecast monthly average inflow on an one-step-ahead basis. The fuzzy neural network model is shown to provide better representation of the monthly average water inflow forecasting, than the models based on Box-Jenkins method, currently in use on the Brazilian electrical sector.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126166304","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
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