发布求助
文献互助 智能选刊 最新文献

Workshop on Neural Network Applications and Tools最新文献

筛选
英文 中文
Modelling Stock Returns With Neural Networks 用神经网络模拟股票收益
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586052
A. Refenes, A. Zapranis, Y. Bentz
{"title":"Modelling Stock Returns With Neural Networks","authors":"A. Refenes, A. Zapranis, Y. Bentz","doi":"10.1109/NNAT.1993.586052","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586052","url":null,"abstract":"Neural networks have attracted much interest in financial engineering but many multivariate data series remain diflcult to model. In this paper we use a non trivial problem in expsure analysis of share prices to multiple factors to explore the interrelationships among the numerous network and data engineering parameters and we highlight the importance of a careful choice of the indicators used as network inputs. We show how data pre-processing can improve generalisation performance by up to 30.5% and present a \"time-sensitive\" cost function, designed to take into account gradually changing input-output relationships. We give empirical evidence that when it is combined with the right leaMags in the indicators generalisation can be further improved by up to IO. 1 %.","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"89 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126318096","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: 13
Neural Networks: New Tools For Data Analysis ? 神经网络:数据分析的新工具?
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586051
J. C. Bioch, W. Verbeke, M.W. van Dijk
{"title":"Neural Networks: New Tools For Data Analysis ?","authors":"J. C. Bioch, W. Verbeke, M.W. van Dijk","doi":"10.1109/NNAT.1993.586051","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586051","url":null,"abstract":"Neural network models have been successfully used in many disciplines such as psychology, computer science, genetics, linguistics and engineering. Recently neural networks are also applied in economics and consumer psychology. We review the statistical properties of multi-layer networks for a better understanding of the usefulness of neural networks as a tool for data-analysis in the social sciences. As an application we analyze the data in a marketing problem, specifically sales’ people projiles. We compare the results obtained with two type of neural networks: multilayer perceptrons and learning vector quantization networks, with a traditional statistical method, in this case discriminant analysis. Finally, we evaluate the use of neural networks as a research tool in economics and marketing.","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131173702","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
The Interpretation Of Supervised Neural Networks 监督神经网络的解释
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586048
P.J.G. Lisboa, A. Mehridehnavi, P. Martin
{"title":"The Interpretation Of Supervised Neural Networks","authors":"P.J.G. Lisboa, A. Mehridehnavi, P. Martin","doi":"10.1109/NNAT.1993.586048","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586048","url":null,"abstract":"Classij-ication of cancer and normal animal tissues is carried out on the basis of their 'H Nuclear Magnetic Resonance (NMR) spectra with neural networks trained by Back-Error Propagation (BEP), using two direrent costfunctions. A log-likelihood costfinction is shown to result in accurate out-of-sample generalisation with a smaller network than the usual Least Mean Squared (ZMS) error. ntejirst step in the interpretation of the operation of neural networks is to quantiJjr the relevance of the input parameters to the diagnosis of each tissue class. Two techniques for achieving this are investigated, namely the Jacobian method and a logarithmic sensitivity matrix. The latter is demonstrated to result in a clearer signature which is consistent across direrent network architectures and also broadly in agreement with conventional statistical correlations.","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132567692","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: 11
A Neural Network Quality Classifier For Tig Welding Without Filler 无填料Tig焊的神经网络质量分类器
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586059
P. Li, M. Fang, J. Lucas
{"title":"A Neural Network Quality Classifier For Tig Welding Without Filler","authors":"P. Li, M. Fang, J. Lucas","doi":"10.1109/NNAT.1993.586059","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586059","url":null,"abstract":"A neural network based on error back propagation learning algorithm has been successfully trained and tested as a quality classifier for TIG welding of stainless steel without filler. The classifer consists of two parallelly connected sub-networks, one for the quality of bead penetration and the other for bead profile. The criterion for the termination of training and the decision rule for the network prediction are self-consistent and are both related to the error tolerance used during training. Three types of borders between the desired classes have been predicted. In contrast to conventional understanding, the accuracy of the classifier can be improved and the size of the borders be reduced by choosing a relatively large error tolerance.","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115310185","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
Adaptive Antenna Beamforming Arrays Using Artificial Neural Networks 基于人工神经网络的自适应天线波束形成阵列
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586046
P. Wells, P.C.J. Hill
{"title":"Adaptive Antenna Beamforming Arrays Using Artificial Neural Networks","authors":"P. Wells, P.C.J. Hill","doi":"10.1109/NNAT.1993.586046","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586046","url":null,"abstract":"Estimation of the angle of am'val (AOA) of radio signals to an antenna array is currently determined by classical spectral, paramehic or eigen-decomposition techniques [ I ] , Neural networks can provide an alternative inverse processing solution allowing the AOA to be determined directly from the received signal data. Moreover, suitably modified layered networks can actually eliminate the need for weight training entirely .","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125789788","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 Neural Predictive Controller For Underwater Robotic Applications 用于水下机器人的神经预测控制器
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586063
V. Kodogiannis, P.J.G. Lisboa, J. Lucas
{"title":"A Neural Predictive Controller For Underwater Robotic Applications","authors":"V. Kodogiannis, P.J.G. Lisboa, J. Lucas","doi":"10.1109/NNAT.1993.586063","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586063","url":null,"abstract":"Oceanographic exploration is one of the fast emerging applications of robotics. The design of Underwater Robotic Vehicles (URV’s), is as challenging as for land based ones. The dificulties in modelling an URV and its hazardous environment restrict the use of conventional controllers. In this paper the application of Neural networks (NNs) for the modelling and control of a prototype URV, which is an example of a system containing non-linearities, is described. A NN model is developed and then incorporated into a predictive control strategy which it is evaluated both in simulation and on-line. Results are shown for both the modelling and control of the system, including hybrid control strategies which combine neural predictive with conventional three term controllers.","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123796249","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
An Intelligent Fuzzy Logic Controller For One-dimension Motion Control 用于一维运动控制的智能模糊控制器
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586064
C. M. Dimitriadis, J. Lygouras, P.G. Tsalides
{"title":"An Intelligent Fuzzy Logic Controller For One-dimension Motion Control","authors":"C. M. Dimitriadis, J. Lygouras, P.G. Tsalides","doi":"10.1109/NNAT.1993.586064","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586064","url":null,"abstract":"The implementation of a fuzzy logic controller for I-D motion control is presentred in this paper. Two difSerent control schemes are described. The first one uses a pure fuuy controller, its output being the control signal for the system. The 7x7 fuzzy matrix assigns the controller output with respect t(o the error value and its derivative. The control curve of the system was produced based on the knowledge derived from the observation of the behaviour of the real system. The second scheme and the most interesting one, is described as a two level controller. The lower level consists of a conventional PID controller, whereas the higher level consits of the fuzzy controller acting over the parameters of the lower level controller. A variety of input signals have been applied fo the system with very satisfactory responses. Furthermore, the simulation results are in very good agreement with those obtained experimentally.","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125368778","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
The Kodiag System Case-based Diagnosis With Kohonen Networks 基于Kohonen网络的Kodiag系统病例诊断
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586057
J. Rahmel, A. von Wangenheim
{"title":"The Kodiag System Case-based Diagnosis With Kohonen Networks","authors":"J. Rahmel, A. von Wangenheim","doi":"10.1109/NNAT.1993.586057","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586057","url":null,"abstract":"This paper describes the case-based KoDiag system, a diagnostic tool based on the Kohonen model of artificial neural networks (ANN), extended by modifications to increase storage capacity and processing speed during learning. A new training method is introduced, that leads to clustering in the Kohonen map according to the feature context and improves performance during the diagnosis process when input data is partially not available. Unlike common ANN-approaches to diagnosis, KoDiag contains both a classification and a test selection component. The classi3cation results of KoDiag are compared to a CBR-expert system.","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133251515","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
Improved Image Compression Using Backpropagation Networks 利用反向传播网络改进图像压缩
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586056
G. Qiu, T. Terrell, M. Varley
{"title":"Improved Image Compression Using Backpropagation Networks","authors":"G. Qiu, T. Terrell, M. Varley","doi":"10.1109/NNAT.1993.586056","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586056","url":null,"abstract":"This paper describes an improved image compression scheme using backpropagation networks. The new scheme is aimed at improving the networks' generalisation capabilities, thereby enabling them to effectively compress a wide range of novel images. The networks operate, and are trained on, residual image blocks, thus eliminating the problem of varying average image intensities highlighted by Cottrell et al. Tabulated experimental results and example reconstructed novel images, for the method of [3] and the new technique, are presented, which demonstrate the improved image compression performance gained using this new technique. 131.","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114619957","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
Prototype Of A Neuro-fuzzy Controlled Model Lorry 神经模糊控制模型卡车的原型
Workshop on Neural Network Applications and Tools Pub Date : 1993-09-13 DOI: 10.1109/NNAT.1993.586065
R. Weissgarber
{"title":"Prototype Of A Neuro-fuzzy Controlled Model Lorry","authors":"R. Weissgarber","doi":"10.1109/NNAT.1993.586065","DOIUrl":"https://doi.org/10.1109/NNAT.1993.586065","url":null,"abstract":"","PeriodicalId":164805,"journal":{"name":"Workshop on Neural Network Applications and Tools","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123337465","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：481959085
Book学术官方微信