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
A biologically inspired connectionist system for natural language processing 一个受生物学启发的自然语言处理连接主义系统
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181485
J. Rosa
{"title":"A biologically inspired connectionist system for natural language processing","authors":"J. Rosa","doi":"10.1109/SBRN.2002.1181485","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181485","url":null,"abstract":"Nowadays artificial neural network models often lack many physiological properties of the nervous cell. Current learning algorithms are more oriented to computational performance than to biological credibility. The aim of this paper is to propose an artificial neural network system, called Bio-/spl theta/R, including architecture and algorithm, to take care of a natural language processing problem, the thematic relationship, in a biologically inspired connectionist approach. Instead of feedforward or simple recurrent network, it is presented as a bi-directional architecture. Instead of the well-known biologically implausible backpropagation algorithm, a neurophysiologically motivated one is employed to account for linguistic thematic role assignment in natural language sentences. In addition, several features concerning biological plausibility are also included.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"87 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":"115684961","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: 12
An investigation of fuzzy combiners applied to a hybrid multi-neural system 模糊组合器在混合多神经系统中的应用研究
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181462
A. Canuto, M. Fairhurst, G. Howells
{"title":"An investigation of fuzzy combiners applied to a hybrid multi-neural system","authors":"A. Canuto, M. Fairhurst, G. Howells","doi":"10.1109/SBRN.2002.1181462","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181462","url":null,"abstract":"This papers investigates the performance of some fuzzy combination schemes applied to a multi hybrid neural system which is composed of neural and fuzzy neural networks. An empirical evaluation in a handwritten numeral recognition task is used to investigate the performance of the presented fuzzy methods with some existing combination methods.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"183 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":"116060933","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
A fuzzy approach to support a musculoskeletal disorders diagnosis 支持肌肉骨骼疾病诊断的模糊方法
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181461
Domingos Vanderlei Filho, Marcos A. dos Santos, Teresa B Ludermir, M. Valença
{"title":"A fuzzy approach to support a musculoskeletal disorders diagnosis","authors":"Domingos Vanderlei Filho, Marcos A. dos Santos, Teresa B Ludermir, M. Valença","doi":"10.1109/SBRN.2002.1181461","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181461","url":null,"abstract":"Summary form only given. This work describes a fuzzy inference system to support a musculoskeletal disorders diagnosis. The musculoskeletal disorders refer to conditions that involve the nerves, tendons, muscles and supporting structures of the body. Nowadays, an increasing number of occupational injuries and illness are observed. The linguistic variables and rules of the systems were associated with disease symptoms and signals. To implement this system we incorporated the knowledge of a medical expert. We use some clinical cases to evaluate the performance of our fuzzy model. The fuzzy system used applies the Mamdani method (1975). The next step of our research is to fine tune our system based on the analysis of more input variables and to validate the model against a bigger population of patients with well-confirmed diagnostics.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"27 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":"121432432","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
Fault detection and diagnosis in duals converters applied in DC drives 直流驱动双变换器的故障检测与诊断
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181444
Marlon R. de Gouvêa, L. Baccarini, W. Caminhas
{"title":"Fault detection and diagnosis in duals converters applied in DC drives","authors":"Marlon R. de Gouvêa, L. Baccarini, W. Caminhas","doi":"10.1109/SBRN.2002.1181444","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181444","url":null,"abstract":"Summary form only given. For duals converters of AC or DC drives, faults related with them are important in relation with the available time of equipments. Besides, the speed sensors used as tachogenerator and pulse generator are important factors. This work presents a fault diagnostic and detection system for commutation, short circuit and circuit open faults. Speed sensor faults can also be detected with an automatic feedback reconfiguration. The fault diagnostic and detection system is based in the fuzzy set theory to generate inputs to the neural network responsible for fault classification, and the state observer for sensor speed fault detection. Results obtained from digital simulations conclude that the system is a simple and efficient means for the detection of the proposed faults. Other advantage is that the control system reconfiguration based on the state observers permits the drive system to operate during speed sensor faults. So, this proposed fault detection system is ideal for practical implementation.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"15 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":"123840890","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
Using a chain of LVQ neural networks for pattern recognition of EEG signals related to intermittent photic-stimulation 利用LVQ神经网络链对间歇光刺激相关的脑电信号进行模式识别
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181465
M. Kugler, H. S. Lopes
{"title":"Using a chain of LVQ neural networks for pattern recognition of EEG signals related to intermittent photic-stimulation","authors":"M. Kugler, H. S. Lopes","doi":"10.1109/SBRN.2002.1181465","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181465","url":null,"abstract":"This work reports the use of neural networks for pattern recognition in electroencephalographic signals related to intermittent photic-stimulation. Due to the low signal/noise ratio of this kind of signal, it was necessary the use of a spectrogram as a predictor and a chain of LVQ neural networks. The efficiency of this pattern recognition structure was tested for many different configurations of the neural networks parameters and different volunteers. A direct relationship between the dimension of the neural networks and their performance was observed. Results so far encourage new experiments and demonstrate the feasibility of the proposed system for real-time pattern recognition of complex signals.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"82 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":"124804817","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: 14
Technique to design MLP networks in CMOS technology with adjustment of the backpropagation algorithm 基于CMOS技术的MLP网络设计技术及反向传播算法的调整
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181468
F. A. Pereira, Jés Jesus Fiais Cerqueira
{"title":"Technique to design MLP networks in CMOS technology with adjustment of the backpropagation algorithm","authors":"F. A. Pereira, Jés Jesus Fiais Cerqueira","doi":"10.1109/SBRN.2002.1181468","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181468","url":null,"abstract":"The implementation of CMOS multipliers have been based on the use of either analog circuits for continuous time signal processing or switched current techniques for discrete time processing, once current mode topologies have become a trend for IC designers in low voltage applications. In this work we perform an analysis of some techniques for implementing the basic building blocks in a neural network using the IC technology for analog signal processing. Even though we focus on the operation of MOS devices in the strong inversion region deep into saturation, some aspects of the synapses in the weak inversion region are also explained, which has been accomplished through the use of classical asymptotical models for the drain current.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"8 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":"115826685","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
Automatic gender identification by speech signal using eigenfiltering based on Hebbian learning 基于Hebbian学习的语音信号特征滤波自动性别识别
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181476
R. Fagundes, A.A.C. Martins, F. Castro, M. C. F. D. Castro
{"title":"Automatic gender identification by speech signal using eigenfiltering based on Hebbian learning","authors":"R. Fagundes, A.A.C. Martins, F. Castro, M. C. F. D. Castro","doi":"10.1109/SBRN.2002.1181476","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181476","url":null,"abstract":"This work presents an automatic gender identification algorithm based on eigenfiltering. A maximum eigenfilter is implemented by means of an artificial neural network (ANN) trained via generalized Hebbian learning. The eigenfilter uses the principal component analysis to perform maximum information extraction from the speech signal, which enhances correlated information and improves the pattern analysis. Also, a well known speech processing technique is applied, the mel-frequency cepstral coefficients. This technique is a classical approach for speech feature extraction, and it is a very efficient way to represent physiological voice parameters. The pattern classification uses a radial basis function neural network. Experimental results have shown that the identification algorithm overall performance was widely increased by the eigenfiltering process.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"334 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":"124047312","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
Implementation of probabilistic automata in weightless neural networks 无权重神经网络中概率自动机的实现
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181481
J. C. M. Oliveira, M. D. Souto, Teresa B Ludermir
{"title":"Implementation of probabilistic automata in weightless neural networks","authors":"J. C. M. Oliveira, M. D. Souto, Teresa B Ludermir","doi":"10.1109/SBRN.2002.1181481","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181481","url":null,"abstract":"The objective of this paper is to analyze the practical viability of the theoretical results concerning the relationship between a class of weightless neural networks, known as general single-layer sequential weightless neural networks (GSSWNNs), and the probabilistic automata (PA). This study was based on the theoretical model development by de Souto (1999). This model shows the computational equivalence between the GSSWNNs and PAs. However, in order to develop a practical implementation, it is important to deal with the questioning of whether restrictions on the original theoretical results are necessary.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"2002 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":"127329709","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
Extraction of visual information using maximum likelihood Hebbian learning 利用最大似然Hebbian学习提取视觉信息
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181479
E. Corchado, C. Fyfe
{"title":"Extraction of visual information using maximum likelihood Hebbian learning","authors":"E. Corchado, C. Fyfe","doi":"10.1109/SBRN.2002.1181479","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181479","url":null,"abstract":"We explore an extension of Hebbian learning which has been called /spl epsiv/-insensitive Hebbian learning, and derive lateral connections from a probability density function (PDF). We use these lateral connections to move outputs towards the mode of the PDF and use the resulting outputs to train the feedforward connections. We show that /spl epsiv/-insensitive Hebbian learning may be considered as a special case of maximum likelihood Hebbian learning and investigate the resulting network with both real and artificial data. We finally show that the resulting network is able to identify motion in the environment.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"100 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":"131423164","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
Electrocardiogram pattern recognition by means of MLP network and PCA: a case study on equal amount of input signal types 基于MLP网络和PCA的心电图模式识别:等量输入信号类型的案例研究
VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings. Pub Date : 2002-11-11 DOI: 10.1109/SBRN.2002.1181474
F. Vargas, M. C. F. D. Castro, Marcello Macarthy, D. Lettnin
{"title":"Electrocardiogram pattern recognition by means of MLP network and PCA: a case study on equal amount of input signal types","authors":"F. Vargas, M. C. F. D. Castro, Marcello Macarthy, D. Lettnin","doi":"10.1109/SBRN.2002.1181474","DOIUrl":"https://doi.org/10.1109/SBRN.2002.1181474","url":null,"abstract":"This work proposes a system to help the doctor to detect cardiac arrhythmia. As reference, it uses the normal, fusion and PVC signals of the MIT database. Then, we extract the principal characteristics of the signal by means of the principal component analysis (PCA) technique. One key point in this work is the input signals extraction, which are captured in the same amount. So, the number of segments for each signal is the same. After signal preprocessing, they are applied to a multilayer perceptron (MLP). The MLP with 5 neurons was verified to have the best accuracy. Based on this idea (the use of the same information amount for all input signal types), we achieved better results in comparison with other works in the field. This consideration is very important due to the fact that the ANN could be more sensible to the signal type with major predominance.","PeriodicalId":157186,"journal":{"name":"VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings.","volume":"15 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":"114207412","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: 35
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