发布求助
文献互助 智能选刊 最新文献

International 1989 Joint Conference on Neural Networks最新文献

筛选
英文 中文
Inheritance reasoning in connectionist networks 连接主义网络中的继承推理
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118335
M. Jones, G. A. Story
{"title":"Inheritance reasoning in connectionist networks","authors":"M. Jones, G. A. Story","doi":"10.1109/IJCNN.1989.118335","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118335","url":null,"abstract":"Summary form only given, as follows. A bidirectional network model is described for inheritance reasoning which processes queries by combinations of top-down and bottom-up reasoning. The model, which is based on theoretical work in nonmonotonic reasoning, permits multiple inheritance paths in acyclic inheritance theories and allows an arbitrary preference relation among the inferences in the theory (to handle exceptions, for example). Unlike other inheritance models which compute extensions serially (maximally consistent models), the network gains substantially more parallelism by simultaneously reasoning in multiple extensions when possible.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"35 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":"115791146","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
Efficient implementation of neural networks on Hypercube SIMD arrays 神经网络在超立方体SIMD阵列上的高效实现
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118455
K. Kim, V.K.P. Kumar
{"title":"Efficient implementation of neural networks on Hypercube SIMD arrays","authors":"K. Kim, V.K.P. Kumar","doi":"10.1109/IJCNN.1989.118455","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118455","url":null,"abstract":"Summary form only given, as follows. An efficient parallel implementation of neural networks on Hypercube SIMD arrays is presented. The authors show a mapping of a neural network having n nodes and e connections onto a Hypercube array having (n+e) processing elements such that each update step of the neural network can be performed in 8 log/sub 2/ (n+e)-3 steps by preprocessing the weight matrix. The technique is simple and efficient and can be used on current parallel machines such as the Connection Machine.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"33 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":"115123475","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
Period disambiguation using a neural network 基于神经网络的周期消歧
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118427
T. Humphrey, Fu-qiu Zhou
{"title":"Period disambiguation using a neural network","authors":"T. Humphrey, Fu-qiu Zhou","doi":"10.1109/IJCNN.1989.118427","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118427","url":null,"abstract":"Summary form only given. A problem that has never been addressed in the literature is the problem of machine recognition of sentences in real-world documents (i.e. identifying the beginning and end of a sentence). A description is given of the problem and experiments that show that a feedforward neural network can be trained, using the backpropagation learning algorithm, to disambiguate periods. The authors also present results that indicate that a low training tolerance improves a neural network's ability to generalize at the cost of a dramatic increase in the number of training iterations.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"10 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":"116290651","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: 17
TInMANN: the integer Markovian artificial neural network 整数马尔可夫人工神经网络
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118700
E. David, den Bout, T. Miller
{"title":"TInMANN: the integer Markovian artificial neural network","authors":"E. David, den Bout, T. Miller","doi":"10.1109/IJCNN.1989.118700","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118700","url":null,"abstract":"A massively parallel, all-digital, stochastic digital architecture called TInMANN is described. It performs competitive and Kohonen types of learning at rates as high as 145000 training examples per second regardless of network size. Simulations of TInMANN, both with and without its conscience mechanism activated, demonstrate its effectiveness on a number of example problems.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"38 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":"116296868","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: 34
Parametric connectivity: feasibility of learning in constrained weight space 参数连通性:约束权空间中学习的可行性
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118650
T. Caudell
{"title":"Parametric connectivity: feasibility of learning in constrained weight space","authors":"T. Caudell","doi":"10.1109/IJCNN.1989.118650","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118650","url":null,"abstract":"Consideration is given to the impact on the performance of selected learning algorithms when specific artificial neural models are constrained. The particular model of constraint under consideration is parametric connectivity (PC), in which the weights of the incoming links are constrained to be a function of a relatively small number of parameters. This can, in principle, be implemented in an electrooptical system, using such devices as photodetectors, miniature electrooptical cells, and laser diodes. Low-resolution holographic mirrors may be used to direct the global structure of the network architecture. A simulation using PC has been developed. Currently, layered PC networks that implement simple logic functions are being investigated. The performance of networks that use PC units (PCU) is measured. PC is incorporated into the generalized delta rule and into genetic algorithms to measure learning capacity. PC allows almost complete generality in network implementation, while taking advantage of optical system performance.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"24 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":"116362939","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
Enhancing supervised learning algorithms via self-organization 通过自组织增强监督学习算法
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118293
R. M. Holdaway
{"title":"Enhancing supervised learning algorithms via self-organization","authors":"R. M. Holdaway","doi":"10.1109/IJCNN.1989.118293","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118293","url":null,"abstract":"A neural network processing scheme is proposed which utilizes a self-organizing Kohonen feature map as the front end to a feedforward classifier network. The results of a series of benchmarking studies based upon artificial statistical pattern recognition tasks indicate that the proposed architecture performs significantly better than do conventional feedforward classifier networks when the decision regions are disjoint. This is attributed to the fact that the self-organization process allows internal units in the succeeding classifier network to be sensitive to a specific set of features in the input space at the outset of training.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"28 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":"123585477","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
A neural network nonlinear predictor 神经网络非线性预测器
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118507
A. Ukrainec, S. Haykin, J. McGregor
{"title":"A neural network nonlinear predictor","authors":"A. Ukrainec, S. Haykin, J. McGregor","doi":"10.1109/IJCNN.1989.118507","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118507","url":null,"abstract":"Summary form only given, as follows. The authors demonstrate that a backpropagation neural network can be used for nonlinear time series prediction. In a computer experiment an example nonlinear time series is used to teach a network the necessary mapping in a supervised manner. Predictor learning curves are presented, showing successful operation. Improvements to the neural network structure with regard to the reduction of the observed performance deficit are discussed.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"39 2 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":"121931823","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: 9
A neural network for tactile sensing: the Hertzian contact problem 触觉感知的神经网络:赫兹接触问题
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/21.141323
A. J. Worth, R. R. Spencer
{"title":"A neural network for tactile sensing: the Hertzian contact problem","authors":"A. J. Worth, R. R. Spencer","doi":"10.1109/21.141323","DOIUrl":"https://doi.org/10.1109/21.141323","url":null,"abstract":"A neural network has been developed for use with local closed-loop gripper control using a tactile sensor array. The specific task considered is to solve part of the inverse Hertzian contact problem. Backpropagation is used to train a single hidden-layer network to recognize the angle of contact between a cylindrical finger with an embedded sensor array and a cylindrical rod. Simulation results are presented and discussed.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"44 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":"117183615","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: 24
An application of SVM: alphanumeric character recognition 支持向量机的一个应用:字母数字字符识别
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118320
Y. Kato, H. Saito, T. Ejima
{"title":"An application of SVM: alphanumeric character recognition","authors":"Y. Kato, H. Saito, T. Ejima","doi":"10.1109/IJCNN.1989.118320","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118320","url":null,"abstract":"Summary form only given. The application of a stochastic vector machine (SVM) to alphanumeric character recognition is considered. The SVM is a new multilayered network with learning ability as in the backpropagation (BP) model. The system dynamics in the network is represented on the direct product space of the stochastic vector, so the network consists of units and states. The learning rule follows gradient decent formulation so as to minimize Kullback divergence between the output and the desired states. A preliminary recognition experiment on alphabetic characters was conducted, and SVM's internal representations were examined from weight patterns in the network. The experiment indicates that distributed or local representation is developed by the learning algorithm. A network system was constructed and applied to alphanumeric character recognition. Experimental results indicate that the SVM can perform as well as the BP model.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"44 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120867206","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
Neural kinematics net for a redundant robot arm 冗余机械臂的神经运动学网络
International 1989 Joint Conference on Neural Networks Pub Date : 1900-01-01 DOI: 10.1109/IJCNN.1989.118719
R. Eckmiller, J. Beckmann, H. Werntges, M. Lades
{"title":"Neural kinematics net for a redundant robot arm","authors":"R. Eckmiller, J. Beckmann, H. Werntges, M. Lades","doi":"10.1109/IJCNN.1989.118719","DOIUrl":"https://doi.org/10.1109/IJCNN.1989.118719","url":null,"abstract":"Neural net mechanisms are proposed for the geometric representation of the mapping operation of desired 2D trajectories into actuator movements for a four-joint machine (4JM). The 4JM is capable of drawing various trajectories on a desk surface (40 cm*40 cm)-similar to horizontal drawing movements of a human arm-with the vertical projection of the stationary shoulder joint as center of the reference system. In this redundant robot system the four actuators for rotary movements above the joints (shoulder, virtual joint, elbow, and hand) simultaneously receive control signals from the neural kinematics net (NKN). The goal of NKN is to move the fingertip of the 4JM in real time along a desired 2D trajectory as specified by another neural net module, the neural space net.<<ETX>>","PeriodicalId":199877,"journal":{"name":"International 1989 Joint Conference on Neural Networks","volume":"41 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":"125748735","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
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