发布求助
文献互助 智能选刊 最新文献

Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems最新文献

筛选
英文 中文
A neural network model for the evaluation of Dutch non-life insurance companies 荷兰非寿险公司评价的神经网络模型
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499499
B. Kramer
{"title":"A neural network model for the evaluation of Dutch non-life insurance companies","authors":"B. Kramer","doi":"10.1109/ANNES.1995.499499","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499499","url":null,"abstract":"Based on six financial ratios, a one-hidden-layer back-propagation neural network classifies Dutch non-life insurance companies as strong moderate, or weak. The network shows very good performance for weak and strong companies (95% correct), but completely fails to recognize moderate companies. The relative importance of each input variable is analyzed by calculating the strength of the relationship between each input and each output variable.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123241789","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
Radar pulse train parameter estimation and tracking using neural networks 基于神经网络的雷达脉冲序列参数估计与跟踪
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499448
G. Noone
{"title":"Radar pulse train parameter estimation and tracking using neural networks","authors":"G. Noone","doi":"10.1109/ANNES.1995.499448","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499448","url":null,"abstract":"The post-deinterleaving radar pulse train problem requires estimation of the parameters and tracking of the individual pulse trains. A simple recurrent backpropagation neural network is used based on a simple state space time series formulation of the radar problem. The network incorporates a novel heuristic adaptive error threshold that allows simultaneously good tracking and parameter estimating abilities. Two simple but revealing examples are presented to show how the network is robust to missing and spurious pulses, as well as multiple level staggers with discontinuous mode changes.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123815850","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
Genetic optimisation of control parameters of a neural network 神经网络控制参数的遗传优化
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499466
B. Choi, K. Bluff
{"title":"Genetic optimisation of control parameters of a neural network","authors":"B. Choi, K. Bluff","doi":"10.1109/ANNES.1995.499466","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499466","url":null,"abstract":"One of the shortcomings of artificial neural networks (ANNs) is the difficulty in predicting the best control parameters for a certain application. The number of combinations of parameters is very large. This makes it very inefficient and expensive to search manually by trial and error. Genetic algorithms (GAs) are an excellent and effective search technique suitable for this task. This paper describes an investigation into the use of GAs to automate the choice of parameters in both a standard backpropagation (SBP) and a fuzzy backpropagation (FBP) network for different applications.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130668297","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
Increased reliability by effective use of sensor information: a shop floor application of sensor-aided robotic handling 通过有效利用传感器信息提高可靠性:传感器辅助机器人处理的车间应用
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499508
W. Friedrich
{"title":"Increased reliability by effective use of sensor information: a shop floor application of sensor-aided robotic handling","authors":"W. Friedrich","doi":"10.1109/ANNES.1995.499508","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499508","url":null,"abstract":"This paper describes the effective use of low level sensor information to increase reliability and safety for a shop floor application of robotic palletising. The reliability of automated machinery in shop floor applications depends to a great extent on how well the system can respond to unpredictable situations. For any robotic installation one crucial factor for reliable and safe operation is The effective use of sensor information. The following article describes the key factors leading to a reliable robotic palletising operation using examples of implementation details. The palletiser is part of a highly flexible automated blending, filling and storage warehouse system at a Wellington (New Zealand) based oil company. Recent improvements based on previous shop floor experience led to a very robust operation capable of dealing with limited container variations using a simple corrective motion strategy. The control architecture is based on a concept of decentralised control differentiating between handling operations, process requirements and communications between host and sub-systems. This concept allows very short set-up times for future changes involving one or more sub-systems. The present system is user-friendly and simple to operate with status and fault messages displayed in plain English. The gantry system has been designed, implemented and commissioned by Industrial Research Limited. The updated handling system has been operating successfully in shop floor production for over two years now.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114230088","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
Towards a model of multi-agent connectionist hybrid system 多智能体连接混合系统模型研究
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499488
N. Szirbik
{"title":"Towards a model of multi-agent connectionist hybrid system","authors":"N. Szirbik","doi":"10.1109/ANNES.1995.499488","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499488","url":null,"abstract":"A connectionist system that is capable of reasoning about problems posed usually to expert systems is used for the purpose of dynamic cognition tasks. The architecture of such a system must contain \"classical\" AI representations and symbolic information processing entities. Coupling this part of the system with multiple connectionist structures implies a definition for the intercommunication channels, and a specification of the dynamic behavior of the entire system. Some experiments and results are illustrated in an attempt to shed light on the questions raised and the difficulties encountered. The study concludes by contrasting the ideas presented with the mainstream of computational cognitive science.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128396480","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: 2
A neural network that learns to play five-in-a-row 一个能学会玩五行棋的神经网络
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499446
Bernd Freisleben
{"title":"A neural network that learns to play five-in-a-row","authors":"Bernd Freisleben","doi":"10.1109/ANNES.1995.499446","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499446","url":null,"abstract":"A neural network that learns to play the board game of five-in-a-row is presented. The basic idea of the approach is to let an appropriately designed network play a series of games against an opponent and use a reinforcement learning algorithm to train the network to evaluate the non-occupied board positions by rewarding good moves and penalizing bad moves. The performance of the proposed network is demonstrated by presenting experimental results.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132832785","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: 15
Optimal sizing of feedforward neural networks: Case studies 前馈神经网络的最优大小:案例研究
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499444
K. W. Lee, H. Lam
{"title":"Optimal sizing of feedforward neural networks: Case studies","authors":"K. W. Lee, H. Lam","doi":"10.1109/ANNES.1995.499444","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499444","url":null,"abstract":"Feedforward neural networks with sigmoidal hidden layers can be used to approximate any continuous functions within allowable tolerances in accuracy. However no systematic rules are available for the determination of the optimal number of hidden nodes for the networks. An algorithm is proposed which can be employed to find the optimal number of hidden nodes in FNNs used for function approximation. The algorithm has advantages over the conventional trial and error method as the computational time will be reduced and there will be a lower probability of solutions getting stuck at local minima. Two case studies are made to investigate the performance of the algorithm yielding encouraging results.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133242507","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
Integrated planning for computer animation 电脑动画综合策划
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499502
P. Hall, F. Devitt
{"title":"Integrated planning for computer animation","authors":"P. Hall, F. Devitt","doi":"10.1109/ANNES.1995.499502","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499502","url":null,"abstract":"We present a planning system for use in a computer animation environment. The aim of our work is to simulate a human actor by building a broad but shallow artificial intelligence agent. The dual abilities to navigate through a world and solve problems along the way are amongst the key requirements of such an agent. By the novel integration of three planners we have developed an agent that is capable of solving such problems. In addition, we have devised methods by which our agent can detect and react to changes in its environment, and construct beliefs that may be true or false.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"36 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121160222","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
Fuzzy logic and its hardware implementation 模糊逻辑及其硬件实现
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499450
K. Hirota
{"title":"Fuzzy logic and its hardware implementation","authors":"K. Hirota","doi":"10.1109/ANNES.1995.499450","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499450","url":null,"abstract":"The fundamentals of a fuzzy logic circuit and its application to fuzzy inference chips and fuzzy flip flops are mentioned with circuit examples.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124572987","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
Applying machine learning to subject classification and subject description for information retrieval 将机器学习应用于主题分类和主题描述的信息检索
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems Pub Date : 1995-11-20 DOI: 10.1109/ANNES.1995.499481
S. Cunningham, Brent Summers
{"title":"Applying machine learning to subject classification and subject description for information retrieval","authors":"S. Cunningham, Brent Summers","doi":"10.1109/ANNES.1995.499481","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499481","url":null,"abstract":"This paper describes an experiment in applying a standard supervised machine learning algorithm (C4.5) to the problem of developing subject classification rules for documents. This algorithm is found to produce surprisingly concise models of document classifications. While the models are highly accurate on the training sets, evaluation over test sets or through cross-validation shows a significant decrease in classification accuracy. Given the difficult nature of the experimental task, however, the results of this investigation are promising and merit further study. An additional algorithm, 1R, is shown to be highly effective in generating lists of candidate terms for subject descriptions.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121330336","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
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