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
Dynamic modeling of robotic trajectories using the parametrized SOM 基于参数化SOM的机器人轨迹动力学建模
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181471
A. C. Padoan, A. Araujo, G. Barreto
{"title":"Dynamic modeling of robotic trajectories using the parametrized SOM","authors":"A. C. Padoan, A. Araujo, G. Barreto","doi":"10.1109/SBRN.2002.1181471","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181471","url":null,"abstract":"Planning and control of robotic trajectories is an important and open issue. This paper uses an unsupervised neural network model to construct the dynamical modelling of trajectories. A neural network with a short term memory mechanism, was designed to provide the associated joint angles when it receives as input the present and some past states of the robot spatial position. The model uses the self-organizing map (SOM) to approximate the mapping using just some states of the trajectory.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"122 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":"127546874","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
Genetic operators setting for the operation planning of hydrothermal systems 热液系统运行规划的遗传算子设置
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181453
P. Leite, A. Carneiro, A. Carvalho
{"title":"Genetic operators setting for the operation planning of hydrothermal systems","authors":"P. Leite, A. Carneiro, A. Carvalho","doi":"10.1109/SBRN.2002.1181453","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181453","url":null,"abstract":"This paper presents a study of genetic operators used in the operation planning of hydrothermal systems. Such investigation was necessary to define the influence and rate for each genetic operator on the resolution of this problem. In order to adjust genetic algorithms to the problem investigated several traditional genetic operators were adapted. The developed algorithm was applied in real hydrothermal systems, with plants belonging to the Brazilian Southeast system.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"2 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":"124496096","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
Turing machines with finite memory 具有有限记忆的图灵机
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181437
W. R. Oliveira, M. D. Souto, Teresa B Ludermir
{"title":"Turing machines with finite memory","authors":"W. R. Oliveira, M. D. Souto, Teresa B Ludermir","doi":"10.1109/SBRN.2002.1181437","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181437","url":null,"abstract":"Motivated by our earlier work on Turing computability via neural networks (1992, 2001) and the results by Maass et al. (1997, 1998) on the limit of what can be actually computed by neural networks when noise (or limited precision on the weights) is considered, we introduce the notion of definite Turing machine (DTM) and investigate some of its properties. We associate to every Turing machine (TM) a finite state automaton (FSA) responsible for the next state transition and action (output and head movement). A DTM is TM in which its FSA is definite. A FSA is definite (of order k>0) if its present state can be uniquely determined by the last k inputs. We show that DTM are strictly less powerful than TM but are capable to compute all simple functions. The corresponding notion of finite-memory Turing machine is shown to be computationally equivalent to Turing machine.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"23 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":"126556944","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
Autonomous vehicle parking using finite state automata learned by J-CC artificial neural nets 基于J-CC人工神经网络的有限状态自动机自动泊车
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181472
F. Osório, F. Heinen, Luciane Fortes
{"title":"Autonomous vehicle parking using finite state automata learned by J-CC artificial neural nets","authors":"F. Osório, F. Heinen, Luciane Fortes","doi":"10.1109/SBRN.2002.1181472","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181472","url":null,"abstract":"This paper presents the SEVA system, an autonomous vehicle parking simulator. This tool implements a robust control system for autonomous vehicle parking based on the finite-state automata and trained by the Jordan cascade-correlation (J-CC) artificial neural networks.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"45 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":"122357697","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
Modulatory interaction as a support to modeling neural substrates of the decision process 调节相互作用作为建模决策过程的神经基质的支持
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181484
J. D. Filho, Teresa B Ludermir
{"title":"Modulatory interaction as a support to modeling neural substrates of the decision process","authors":"J. D. Filho, Teresa B Ludermir","doi":"10.1109/SBRN.2002.1181484","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181484","url":null,"abstract":"There is experimental evidence of neuronal groups projecting widely in the brain which are associated to state functions, like those involved in attention and mood changes. There has been a growing interest in the discussion of the brain functions as being performed by specialized modular systems that can be recombined. It is also suggested the existence of a dichotomy in the neural substrates, which could result or not in the aversion behavior. In the present work, we propose a model that focus on the interaction between modules. This interaction take the form of a modulatory mechanism. In order to explore this model, our tests were conceived with the aim of representing the transposition of an obstacle by a hypothetical organism.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"109 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":"130314222","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
Neural network applied to the coevolution of the memetic algorithm for solving the makespan minimization problem in parallel machine scheduling 将神经网络应用于模因算法的协同进化，求解并行调度中的最大完工时间最小化问题
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181473
Tatiane Regina Bonfim, A. Yamakami
{"title":"Neural network applied to the coevolution of the memetic algorithm for solving the makespan minimization problem in parallel machine scheduling","authors":"Tatiane Regina Bonfim, A. Yamakami","doi":"10.1109/SBRN.2002.1181473","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181473","url":null,"abstract":"The problem discussed here is one of scheduling the tasks in identical parallel machines. In this problem, we deal with a set of n tasks and m identical parallel machines, with the objective of minimizing the makespan. The makespan is the total processing time of the most busy machine. This work presents an implementation of a memetic-neuro scheduler for solving this scheduling problem. The memetic algorithm, which is an hybrid version of genetic algorithm with local search, has been used to evolve good scheduling forms; and the neural network has been used to calculate the fitness for each individual of the population.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"22 2 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":"124248573","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
The influence of noisy patterns on the performance of learning methods in the splice junction recognition problem 噪声模式对拼接连接识别问题中学习方法性能的影响
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181431
Ana Carolina Lorena, Gustavo E. A. P. A. Batista, A. Carvalho, M. C. Monard
{"title":"The influence of noisy patterns on the performance of learning methods in the splice junction recognition problem","authors":"Ana Carolina Lorena, Gustavo E. A. P. A. Batista, A. Carvalho, M. C. Monard","doi":"10.1109/SBRN.2002.1181431","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181431","url":null,"abstract":"Since the beginning of the Human Genome Project, which aims at sequencing all the human's genetic information, a large amount of sequence data has been generated. Much attention is now given to the analysis of this data. A great part of these analysis is carried out with the use of intelligent computational techniques. However, many of the genetic databases are characterized by the presence of noisy data, which can deteriorate the performance of the computational techniques applied. This work studies the influence of noisy data in the training of three different learning methods: decision trees, artificial neural networks and support vector machines. The task investigated is the recognition of splice junctions in DNA sequences, which is part of the gene identification problem. Results indicate that the elimination of noisy patterns from the dataset can improve the learning algorithms' performance, with no significant reduction in their generalization ability.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"32 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":"122565406","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
Aggregation algorithms for neural network ensemble construction 神经网络集成构建的聚合算法
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181466
P. Granitto, P. F. Verdes, H. Navone, H. Ceccatto
{"title":"Aggregation algorithms for neural network ensemble construction","authors":"P. Granitto, P. F. Verdes, H. Navone, H. Ceccatto","doi":"10.1109/SBRN.2002.1181466","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181466","url":null,"abstract":"How to generate and aggregate base learners to have optimal ensemble generalization capabilities is an important questions in building composite regression/classification machines. We present here an evaluation of several algorithms for artificial neural networks aggregation in the regression settings, including new proposals and comparing them with standard methods in the literature. We also discuss a potential problem with sequential algorithms: the non frequent but damaging selection through their heuristics of particularly bad ensemble members. We show that one can cope with this problem by allowing individual weighting of aggregate members. Our algorithms and their weighted modifications are favorably tested against other methods in the literature, producing a performance improvement on the standard statistical databases used as benchmarks.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"162 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":"128164708","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 Connect 4 - a connectionist approach to the game 神经连接4 -一个连接的方法来游戏
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181482
M. Schneider, J. Rosa
{"title":"Neural Connect 4 - a connectionist approach to the game","authors":"M. Schneider, J. Rosa","doi":"10.1109/SBRN.2002.1181482","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181482","url":null,"abstract":"This article presents the system \"Neural Connect 4\", a program that plays the game Connect Four. This system employs the multilayer perceptron architecture which learns through the supervised backpropagation algorithm. The required knowledge for training comes from saved games. After a short introduction to the game itself, the symbolic algorithms used for training and evaluation are described. Comparisons are made within a connectionist approach: effective and ineffective learning techniques are shown, and the results are discussed. \"Neural Connect 4\" proves that artificial neural networks are completely adequate for learning Connect Four, given that certain principles are observed.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"55 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":"131704978","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
Forecasting the IBOVESPA using NARX networks and random walk model 利用NARX网络和随机游走模型预测IBOVESPA
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181449
E. Oliveira, Teresa B Ludermir
{"title":"Forecasting the IBOVESPA using NARX networks and random walk model","authors":"E. Oliveira, Teresa B Ludermir","doi":"10.1109/SBRN.2002.1181449","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181449","url":null,"abstract":"The objective of this work was to apply an important class of nonlinear systems for discrete time, called NARX networks, to carry through accurate forecasts of the daily maximum price series in the IBOVESPA, since it depends on random, nonlinear and multivariate factors, making it difficult to forecast using the conventional techniques.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"85 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":"126242119","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