Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97最新文献_第8页

Extracting stochastic machines from recurrent neural networks trained on complex symbolic sequences 从复杂符号序列训练的递归神经网络中提取随机机器

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619435

P. Tiňo, V. Vojtek

引用次数: 13

Rule extraction from trained artificial neural network with functional dependency preprocessing 基于函数依赖预处理的人工神经网络规则提取

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619437

S. Geva, M. T. Wong, M. Orlowski

{"title":"Rule extraction from trained artificial neural network with functional dependency preprocessing","authors":"S. Geva, M. T. Wong, M. Orlowski","doi":"10.1109/KES.1997.619437","DOIUrl":"https://doi.org/10.1109/KES.1997.619437","url":null,"abstract":"The paper describes a technique to extract symbolic rules from a trained artificial neural network with functional dependency preprocessing. RULEX (R. Andrews and S. Geva, 1994; 1995), classified as a decompositional technique of rule extraction from trained neural network in a recent survey by R. Andrews et al. (1995), is used to extract symbolic rules from data that have been preprocessed by identification of functional dependency. The identification of functional dependency offers several advantages. It can lead to significant reductions in the computational load, to reduction in the number and complexity of derived rules and to the discovery of alternative solutions that would otherwise be ignored by some methods due to implicit or explicit procedural bias. Benchmark datasets from the UCI repository of machine learning databases are used in the testing. Experimental results indicate that by including functional dependency preprocessing performance of RULEX can be improved. Good rule quality is obtained by applying RULEX with functional dependency preprocessing when compared to symbolic rule extraction technique C4.5.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124488477","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

Generation of fuzzy k-partitions based on tolerance relations and maximal consistency 基于容差关系和最大一致性的模糊k分区的生成

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619412

T. Murai, A. Kitada, Yoshiharu Sato

引用次数: 2

High speed intelligent machine through programmable hardware: application to genomic systems 通过可编程硬件的高速智能机器:在基因组系统中的应用

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619446

E. Lemoine, L. Maillet-Contoz, D. Merceron, J. Sallantin

引用次数: 0

An automated matching technique for fingerprint identification 指纹识别的自动匹配技术

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616876

D. Mital, E. Teoh

引用次数: 21

A fuzzy controller using floating membership functions for the braking of a long haul train 基于浮动隶属函数的长途列车制动模糊控制器

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619423

G. Horwood, D. Kearney, Z. Nedic

引用次数: 1

Industrial robotic systems with fuzzy logic controller and neural network 基于模糊逻辑控制器和神经网络的工业机器人系统

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619443

Sang-Bae Lee

{"title":"Industrial robotic systems with fuzzy logic controller and neural network","authors":"Sang-Bae Lee","doi":"10.1109/KES.1997.619443","DOIUrl":"https://doi.org/10.1109/KES.1997.619443","url":null,"abstract":"Generally, when we control the robot, we should calculate exact inverse kinematics. However, inverse kinematics calculation is complex and it takes much time for the manipulator to control in real time. Therefore, the calculation of inverse kinematics can result in a significant control delay in real time. We present a method in which inverse kinematics can be calculated through fuzzy logic mapping, based on an exact solution through fuzzy reasoning instead of inverse kinematics calculation. Also, the result provides sufficient precision and transient tracking error can be controlled based on a fuzzy adaptive scheme. We also demonstrate that neural networks can be used effectively for the control of a nonlinear dynamic system with uncertain or unknown dynamics models and applied to the control robot. The advantage of using the neural approach over the conventional inverse kinematics algorithms is that neural networks can avoid time consuming calculations. We represent a good control efficiency through simulation of a 2-DOF manipulator by fuzzy logic controller, and demonstrate the effectiveness of the proposed learning scheme using feedforward neural networks, too.","PeriodicalId":166931,"journal":{"name":"Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123700847","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

Fuzzy logic based reinforcement learning of admittance control for automated robotic manufacturing 基于模糊逻辑的自动化机器人导纳控制强化学习

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619426

S. Prabhu, D. Garg

引用次数: 11

A neuro-sliding control approach for a class of nonlinear systems 一类非线性系统的神经滑动控制方法

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.619406

Hongliu Du, S. Nair

引用次数: 6

Fuzzy hierarchical car-model pattern recognition system using fixation feedback 基于注视反馈的模糊层次车模模式识别系统

Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97 Pub Date : 1997-05-27 DOI: 10.1109/KES.1997.616879

Y. Arai, G. Sekiguchi, K. Hirota

引用次数: 1