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
CDMA and TDMA based neural nets 基于CDMA和TDMA的神经网络
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889717
Juan Carlos Herrero
{"title":"CDMA and TDMA based neural nets","authors":"Juan Carlos Herrero","doi":"10.1109/SBRN.2000.889717","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889717","url":null,"abstract":"One of the main problems in neural nets implementation is how to take the information from the processing units where it is generated to other processing units, in order for the net to carry on the computation and eventually yield a result. This problem is significant enough to influence the whole physical design, thus we find a wide choice of solutions. This paper's two proposals come from the rising field of wireless communications: CDMA and TDMA. The principles were established long ago, but they have acquired a renewed presence due to the rapidly increasing demand for mobile phones. We are going to see how CDMA and TDMA could apply to neural nets, by means of currently available technology, if we give up the concept \"connection\" between units and grasp the concept \"messages\" exchanged between them, to open the door to neural nets with higher number of processing units and flexible configuration.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"41 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":"126593746","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
Influence of training sample preprocessing in generalization accuracy of multilayer perceptron 训练样本预处理对多层感知器泛化精度的影响
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889753
E. Gasca, R. Barandela
{"title":"Influence of training sample preprocessing in generalization accuracy of multilayer perceptron","authors":"E. Gasca, R. Barandela","doi":"10.1109/SBRN.2000.889753","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889753","url":null,"abstract":"Summary form only given. In this paper the behavior of multilayer perceptron (backpropagation algorithm) generalization accuracy using different pre-processing methods of training sample is investigated. In the experiments, diverse techniques were used. These were separated in two groups: the first one contains those that select a subset of the original sample; the second one clusters techniques whose starting point is a group of codebook prototypes. The tests were carried our with real and artificial data, corresponding to different types of problems. Experimental results show that the combination of both types of procedures gives, in most cases, the best behavior, that is, when it executes an initial filtering with methods of the first group, and later a technique of the second group is applied.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"44 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":"124674825","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 integrated approach of visual computational modelling 视觉计算建模的综合方法
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889765
Iara Moema Oberg Vilela
{"title":"An integrated approach of visual computational modelling","authors":"Iara Moema Oberg Vilela","doi":"10.1109/SBRN.2000.889765","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889765","url":null,"abstract":"Introduces a high level model of visual perception, based on a multidisciplinary approach. The purpose of this model is to extract and to integrate some of the properties of the visual process that incorporates its flexibility and autonomy. Its structure includes a figurative component, which builds the mental representation of the surroundings, and an operative component, which regulates and guides the whole process. Each one of the components is subdivided in three hierarchical levels. The lower level is based on the organism topology, the higher one is based on the external three dimensional space. The intermediate performs the transition between the others. These high level modules can be implemented with computational models already designed and tested that can be found in the literature on visual computational research.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"58 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":"128802405","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
Synthesis of analog circuits using evolutionary hardware 利用进化硬件合成模拟电路
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889721
Fabio A. Salazar, A. C. M. Filho
{"title":"Synthesis of analog circuits using evolutionary hardware","authors":"Fabio A. Salazar, A. C. M. Filho","doi":"10.1109/SBRN.2000.889721","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889721","url":null,"abstract":"The use of the genetic algorithm as a tool for the automatic synthesis of analog circuits is investigated. The advantages and modifications that can be introduced in the standard genetic algorithm, to improve its performance in this specific application, are discussed. The synthesis of an ideal active low pass filter is used as a test example to emphasize the characteristics and limitations of the genetic algorithm. To improve the simulation time a high level synthesis approach, based on behavioral modeling of the active circuit components, is proposed. The circuit coding is based on the use of adjacency matrices in order to reduce the number of \"non-simulable\" circuits.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"32 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":"128642616","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
Neural network-based controllers for mobile robot 基于神经网络的移动机器人控制器
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889712
Celso de Sousa Júnior, E. M. Hemerly
{"title":"Neural network-based controllers for mobile robot","authors":"Celso de Sousa Júnior, E. M. Hemerly","doi":"10.1109/SBRN.2000.889712","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889712","url":null,"abstract":"A neural network-based control approach for mobile robot is proposed. The weight adaptation is made online, without previous learning. Several possible situations in robot navigation are considered,including uncertainties in the model and presence of disturbance. Weight adaptation laws are presented as well as simulation results.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"15 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":"122952326","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
Prediction of protein structures using a Hopfield network 利用Hopfield网络预测蛋白质结构
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889756
L. Scott, J. Chahine, J. Ruggiero
{"title":"Prediction of protein structures using a Hopfield network","authors":"L. Scott, J. Chahine, J. Ruggiero","doi":"10.1109/SBRN.2000.889756","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889756","url":null,"abstract":"Summary form only given. Under proper conditions, a globular protein adopts a unique 3D structure that is encoded in an amino acid sequence. The theoretical prediction of this structure, and the pathways followed during the folding process, are an important problem in structural molecular biology. Several works have explored the application of genetic algorithms and neural networks to the determination of the protein structure. There are several techniques of computational simulation that can be used to study structure of proteins; methods of Monte Carlo, simulated annealing, genetic algorithms and neural networks. This work discusses the possibilities to use neural networks in the study of macromolecule structures and presents a example of a Hopfield network to predict the structure of a protein and discusses the results and possible future works using neural networks and genetic algorithms to design new proteins and drugs. This paper used a Hopfield network to predict a primary sequence and the tertiary structure of the core of the cytochrome b/sub 562/. The neural network was implemented using the programming language C and the simulations were run on Silicon Graphics.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"42 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":"121180501","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
A new paradigm for the description of image patterns-from pixels to fuzzy sets of rules 描述图像模式的新范例——从像素到模糊规则集
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889739
P. Salgado, J. Barroso, J. Bulas-Cruz, P. Melo-Pinto
{"title":"A new paradigm for the description of image patterns-from pixels to fuzzy sets of rules","authors":"P. Salgado, J. Barroso, J. Bulas-Cruz, P. Melo-Pinto","doi":"10.1109/SBRN.2000.889739","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889739","url":null,"abstract":"A paradigm for the description of image patterns is presented: it is proposed that images are described by fuzzy IF...THEN rules instead of pixel values. This approach may benefit from recognised fuzzy systems' superior incorporation of measurement uncertainties, greater resources for managing complexity and better ability to deal with natural language. The concept of relevance has been proposed as a measure of the relative importance of sets of rules (Salgado, 1999, and Salgado et al., 2000). Based on this concept a new methodology was developed: SLIM (separation of linguistic information methodology) (Salgado, 1999, and Salgado et al., 2000). An algorithm implementing SLIM is presented in this paper, derived from the fuzzy C-means clustering algorithm, here applied to organise the fuzzy IF...THEN rules that describe the image. The Lena and the Abington Cross images have been successfully used to illustrate the identification process. The proposed SLIM algorithm has been successfully applied to illustrate a segmentation operation in the \"fuzzy rules domain\", using the Abington Cross image.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"49 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":"133395717","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
A chemical reactor benchmark for parallel adaptive control using feedforward neural networks 基于前馈神经网络的化工反应器基准并行自适应控制
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889711
D. Cajueiro, E. M. Hemerly
{"title":"A chemical reactor benchmark for parallel adaptive control using feedforward neural networks","authors":"D. Cajueiro, E. M. Hemerly","doi":"10.1109/SBRN.2000.889711","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889711","url":null,"abstract":"This paper applies a parallel scheme for adaptive control that uses only one neural network to a CSTR (continuous stirred tank reactor). Convergence of the identification error is investigated by Lyapunov's second method. The training process of the neural network is carried out by using two different techniques: backpropagation and extended Kalman filter algorithm.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"13 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":"131717341","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
Averaging spectra to improve the classification of the noise radiated by ships using neural networks 利用神经网络对舰船辐射噪声进行平均光谱分类
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889731
W. Soares-Filho, J. Seixas, L. Calôba
{"title":"Averaging spectra to improve the classification of the noise radiated by ships using neural networks","authors":"W. Soares-Filho, J. Seixas, L. Calôba","doi":"10.1109/SBRN.2000.889731","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889731","url":null,"abstract":"The noise radiated from ships in the ocean contains information about their machinery, being normally used for detection and identification purposes. In this work we use a neural classifier to identify the radiated noise received by a hydrophone that was far from the ship. The classification is performed in the frequency domain using a feedforward neural network, which is trained using the backpropagation algorithm. It is shown that the use of an averaged spectral information during the production phase improves significantly the efficiency of the classifier, when it is compared to a neural classifier that processes frequency domain data obtained from individual acquisition windows.","PeriodicalId":448461,"journal":{"name":"Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks","volume":"54 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":"115274659","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
Constructing software autonomous agents to computer network management 构建计算机网络管理软件自治代理
Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks Pub Date : 2000-01-22 DOI: 10.1109/SBRN.2000.889755
A. S. M. D. Franceschi, J. Barreto, M. Roisenberg
{"title":"Constructing software autonomous agents to computer network management","authors":"A. S. M. D. Franceschi, J. Barreto, M. Roisenberg","doi":"10.1109/SBRN.2000.889755","DOIUrl":"https://doi.org/10.1109/SBRN.2000.889755","url":null,"abstract":"Summary form only given. There are three important concepts in the computer network management area: managers, agents and managed objects. This work presents a methodology to develop autonomous agents for network management. There are two kinds of agents to develop: static or dynamic agents. The first one can be implemented, using heuristics obtained from an expert or the network administrator, through production rules or feedforward neural networks. Using the network examples we can construct dynamic agents. The recurrent neural network may be trained to solve a problem using some examples. Moreover, the behavior of the management must be considered, the network management may be reactive or proactive. From the analysis it is possible to define if the problem demands static or dynamic autonomous agents. The application of a static approach in the solution of dynamic problems cause two inconveniences: 1) it does not allow covering all the different states of a dynamic system; and 2) to cover all the states it would require a great neural network, perhaps impossible of converging to a solution.","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":"117031309","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
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