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
A neural network-based direct inverse control for active control of vibrations of mechanical systems 基于神经网络的机械系统振动主动控制直接逆控制
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889722
G. Abreu, R. L. Teixeira, J. F. Ribeiro
{"title":"A neural network-based direct inverse control for active control of vibrations of mechanical systems","authors":"G. Abreu, R. L. Teixeira, J. F. Ribeiro","doi":"10.1109/SBRN.2000.889722","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889722","url":null,"abstract":"This paper describes the use of artificial neural networks for the control of vibrations of a mechanical system using its experimental direct inverse model. The neural controller is trained to model the experimental inverse model of the plant using the backpropagation algorithm with simulated annealing. The inverse model of the plant is obtained by the training mechanism that uses experimental input and output data. After the training, the neural network is used as a forward controller. The efficiency and the robustness of the controller are shown through experimental tests. The neural control algorithm is implemented in a computer and the performance of controller is evaluated under a set of experimental tests made to the active control of vibrations of a mechanical system of one degree of freedom actuated by magnetic actuators.","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":"128580747","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: 19
A dynamically coupled chaotic oscillatory correlation network 动态耦合混沌振荡相关网络
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889715
Liang Zhao
{"title":"A dynamically coupled chaotic oscillatory correlation network","authors":"Liang Zhao","doi":"10.1109/SBRN.2000.889715","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889715","url":null,"abstract":"In this paper, a network of dynamically coupled chaotic maps for scene segmentation is proposed. It is a two-dimensional array consisting of discrete chaotic elements. Time evolution of chaotic maps corresponding to an object in the given scene are synchronized and desynchronized with respect to time evolution of chaotic elements corresponding to different objects. As a continuous chaotic oscillatory correlation network, this model can escape from the synchrony-desynchrony dilemma and so has unbounded capacity of segmentation too. In the present model, coupling range of each active element dynamically increases according to predefined rules, until a saturated state is achieved, i.e., locally coupled chaotic maps corresponding to an object at the start are coupled globally at the end. Consequently, both of the advantages of global coupling and local coupling are incorporated in a unique scheme. Another significant result is that good performance and transparent dynamics of the model are obtained by utilizing only one-dimensional chaotic map instead of complex neurons as each element.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"18 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":"128018062","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 fuzzy threshold max-product unit, with learning algorithm, for classification of pattern vectors 基于学习算法的模糊阈值最大积单元模式向量分类
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889740
R. Brouwer
{"title":"A fuzzy threshold max-product unit, with learning algorithm, for classification of pattern vectors","authors":"R. Brouwer","doi":"10.1109/SBRN.2000.889740","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889740","url":null,"abstract":"Proposes a max-product threshold unit (maptu) that, like a single perceptron, can perform dichotomous classifications of pattern vectors. Maptu classifies a pattern vector, x, by determining whether x max-prod w is less than 0.5 or greater than 0.5. Here w, consisting of non-negative values, is referred to as the weight vector. As part of training w is found by setting it equal to c* 0.5/max X/sup -/. X/sup -/ is the matrix whose rows are the training patterns belonging to class-. Maximization is done within the columns of X/sup -/. Since (x max-prod w<0.5) vs. (x max-prod w>0.5) is not symmetrical because the former is much more restrictive than the latter a satisfiability factor based on X/sup -/ and X/sup +/ is calculated to determine which set of training data should be labeled class-and which should be labeled class/sup +/. Let X/sup +/ denote the matrix whose rows are the training patterns belonging to class/sup +/. The only iteration is involved in finding c by trying values greater than 0 near 1. The method is tried with success on 4 different sets of data. Results obtained by other methods in classification of this data is used for comparison to the method using maptu.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"18 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":"121154901","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
Adaptation of parameters of BP algorithm using learning automata 基于学习自动机的BP算法参数自适应
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889708
H. Beigy, M. Meybodi
{"title":"Adaptation of parameters of BP algorithm using learning automata","authors":"H. Beigy, M. Meybodi","doi":"10.1109/SBRN.2000.889708","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889708","url":null,"abstract":"The backpropagation (BP) algorithm is a systematic method for training multilayer neural networks. Despite the many successful applications of backpropagation, it has many drawbacks. For complex problems it may require a long time to train the networks, and it may not train at all. Long training time can be the result of the non-optimal parameters. It is not easy to choose appropriate value of the parameters for a particular problem. In the paper, by interconnection of fixed structure learning automata (FSLA) to the feedforward neural networks, we apply learning automata scheme for adjusting these parameters based on the observation of random response of neural networks. The main motivation in using learning automata as an adaptation algorithm is to use its capability of global optimization when dealing with multi-model surface. The feasibility of proposed method is shown through simulations on three learning problems: exclusive-or, encoding problems, and digit recognition. The simulation results show that the adaptation of these parameters using this method not only increases the convergence rate of learning but it increases the likelihood of escaping from the local minima.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"29 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":"134410251","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: 23
Comparing different clustering techniques-RBF networks training 比较不同聚类技术- rbf网络训练
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889743
M. M. Brizzotti, A. Carvalho
{"title":"Comparing different clustering techniques-RBF networks training","authors":"M. M. Brizzotti, A. Carvalho","doi":"10.1109/SBRN.2000.889743","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889743","url":null,"abstract":"Clustering techniques have a strong influence on the performance achieved by RBF neural networks. The article compares the performance achieved by RBF networks using seven different clustering techniques. For such, different sizes of RBF networks are trained and tested using an automatic target recognition data set. The performances of these RBF networks using each clustering technique are compared and analyzed.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"2 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":"134416437","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
Hypermedia intelligent system 超媒体智能系统
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889757
V. D. R. Junior, Emmanuel L. P. Passos, F. H. Fukuda, E. Antonio, L. Neto, L. Chiganer
{"title":"Hypermedia intelligent system","authors":"V. D. R. Junior, Emmanuel L. P. Passos, F. H. Fukuda, E. Antonio, L. Neto, L. Chiganer","doi":"10.1109/SBRN.2000.889757","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889757","url":null,"abstract":"Summary form only given. In this article techniques are developed together for use of hypermedia systems with techniques of artificial intelligence. The hypermedia intelligent system (HIS) uses the language HTML and, consequently, such related systems as Java, JavaScript, VBScript, Shockwave, among others. A system servant can be used locally, in the Internet or in a intranet. This article presents the operation and a route for the tool maid's use, and studies of cases on three real problems not very explored by techniques of artificial intelligence: neuropsychomotor infant test, analysis of the possibility of registration in university and action analysis for suggestion of acupuncture points.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"122 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":"114592861","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
Elastic neural net algorithm for cluster analysis 聚类分析的弹性神经网络算法
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889737
R. Salvini, L. A. V. Carvalho
{"title":"Elastic neural net algorithm for cluster analysis","authors":"R. Salvini, L. A. V. Carvalho","doi":"10.1109/SBRN.2000.889737","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889737","url":null,"abstract":"Proposes a method for data clustering in a n-dimensional space using the elastic net algorithm which is a variant of the Kohonen topographic map learning algorithm. The elastic net algorithm is a mechanical metaphor in which an elastic ring is attracted by points in a bi-dimensional space while their internal elastic forces try to shun the elastic expansion. The different weights associated with these two kinds of forces lead the elastic to a gradual expansion in the direction of the bi-dimensional points. In this method, the elastic net algorithm is employed with the help of a heuristic framework that improves its performance for application in the n-dimensional space of cluster analysis. Tests were made with two types of data sets: (1) simulated data sets with up to 1000 points randomly generated in groups linearly separable with up to dimension 10 and (2) the Fisher Iris Plant database, a well-known database referred to in the pattern recognition literature. The advantages of the method presented are its simplicity, its fast and stable convergence, beyond efficiency in cluster analysis.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"18 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":"128929209","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
Symbolic regression via genetic programming 通过遗传程序实现符号回归
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889734
D. A. Augusto, H. Barbosa
{"title":"Symbolic regression via genetic programming","authors":"D. A. Augusto, H. Barbosa","doi":"10.1109/SBRN.2000.889734","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889734","url":null,"abstract":"Presents an implementation of symbolic regression which is based on genetic programming (GP). Unfortunately, standard implementations of GP in compiled languages are not usually the most efficient ones. The present approach employs a simple representation for tree-like structures by making use of Read's linear code, leading to more simplicity and better performance when compared with traditional GP implementations. Creation, crossover and mutation of individuals are formalized. An extension allowing for the creation of random coefficients is presented. The efficiency of the proposed implementation was confirmed in computational experiments which are summarized in the paper.","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":"129030462","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: 122
Weight structure of binary codes and the performance of blind search algorithms 二进位码的权值结构及盲搜索算法的性能
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/SBRN.2000.889729
F. M. de Assis
{"title":"Weight structure of binary codes and the performance of blind search algorithms","authors":"F. M. de Assis","doi":"10.1109/SBRN.2000.889729","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889729","url":null,"abstract":"Algebraic block codes are vector linear subspaces defined over a finite field. The original problem of the block codes applied was that of protecting information against error during transmission over communication channels. However, combinatorial coding theory is an independent area of investigations. Algebraic codes own fertile geometric properties. Packing and covering radii are two important parameters of an algebraic code. In the author's previous paper (1997), two inequalities relating these parameters with thoroughness and sparsity of a blind search algorithm were established. In this paper we present a closed expression for the thoroughness of a random blind search algorithm in two cases: baseline random search and random blind search guided by an algebraic code. We interpret the \"worst case \" random search approach as a starting point for future research.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124713799","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
An evolutionary immune network for data clustering 数据聚类的进化免疫网络
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/SBRN.2000.889718
Leandro Nunes, F. V. Zuben
{"title":"An evolutionary immune network for data clustering","authors":"Leandro Nunes, F. V. Zuben","doi":"10.1109/SBRN.2000.889718","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889718","url":null,"abstract":"This paper explores basic aspects of the immune system and proposes a novel immune network model with the main goals of clustering and filtering unlabelled numerical data sets. It is not our concern to reproduce with confidence any immune phenomenon, but to show that immune concepts can be used to develop powerful computational tools for data processing. As important results of our model, the network evolved will be capable of reducing redundancy, describing data structure, including the shape of the clusters. The network will be implemented in association with a statistical inference technique, and its performance will be illustrated using two benchmark problems. The paper is concluded with a trade-off between the proposed network and artificial neural networks used to perform unsupervised learning.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117139536","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: 92
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