发布求助
文献互助 智能选刊 最新文献

[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91最新文献

筛选
英文 中文
A stable learning algorithm for recurrent neural networks 递归神经网络的稳定学习算法
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167094
P. Guturu, H. Pareek, P. Ananthraj
{"title":"A stable learning algorithm for recurrent neural networks","authors":"P. Guturu, H. Pareek, P. Ananthraj","doi":"10.1109/TAI.1991.167094","DOIUrl":"https://doi.org/10.1109/TAI.1991.167094","url":null,"abstract":"The authors used the Liapunov approach to derive a new set of sufficient conditions that explain the stability of feedforward networks. A simplification of these conditions results in a new recurrent backpropagation algorithm. This algorithm preserves the local updating characteristic of the original algorithm but is, at the same time, found to be quite effective even for problems which offered resistance to solution by L. B. Almeida's (1987) approach.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130849888","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
Extending the learnability of decision trees 扩展决策树的可学习性
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167034
Tapio Elomaa
{"title":"Extending the learnability of decision trees","authors":"Tapio Elomaa","doi":"10.1109/TAI.1991.167034","DOIUrl":"https://doi.org/10.1109/TAI.1991.167034","url":null,"abstract":"The author concentrates on B. Natarajan's (1991) framework for learning classes of total functions of discrete domains. A. Ehrenfeucht and D. Haussler (1989) have shown that a subclass of decision trees is learnable in the sense defined by L. Valiant (1984). The author generalizes their definitions to m-ary domains and shows that the learnability of restricted decision tree classifiers carries over to the extended model.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114673472","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
Text processing: robust character recognition using calibrated text and diversified feature set 文本处理:使用校准的文本和多样化的特征集进行稳健的字符识别
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167046
D. Hung, Yui-Liang Chen, R. Chen, T. Cheng
{"title":"Text processing: robust character recognition using calibrated text and diversified feature set","authors":"D. Hung, Yui-Liang Chen, R. Chen, T. Cheng","doi":"10.1109/TAI.1991.167046","DOIUrl":"https://doi.org/10.1109/TAI.1991.167046","url":null,"abstract":"An effective algorithm for a high-performance character recognition system for printed text is presented. The system investigates characters with different aspects of the characteristics to optimize recognition performance. The research is implemented by two major phases: pattern learning and character matching. Therefore, it is not only possible to recognize characters, but also to update the database if any new pattern is detected. An initial implementation of all parts of the proposed system is reported, showing an overall recognition rate of 99.9%.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114707065","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
A method for training a feed-forward neural net model while targeting reduced nonlinearity 一种针对减少非线性的前馈神经网络模型的训练方法
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167095
C. Koutsougeras, G. Papadourakis
{"title":"A method for training a feed-forward neural net model while targeting reduced nonlinearity","authors":"C. Koutsougeras, G. Papadourakis","doi":"10.1109/TAI.1991.167095","DOIUrl":"https://doi.org/10.1109/TAI.1991.167095","url":null,"abstract":"In the analysis presented for feedforward neural networks, the causes of problems in the adaptation of current models are examined. A new method for training a feedforward neural net model is introduced. The method encompasses elements of both supervised and unsupervised learning. The development of internal representations is no more an issue tangential to the curve fitting objectives of the other known supervised learning methods. Curve fitting remains as a primary objective but unsupervised learning techniques are also used in order to aid the development of internal representations. The net structure is incrementally formed, thus allowing the formation of a structure of reduced nonlinearity.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131826765","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
A tool for tree pattern matching 树模式匹配工具
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167125
J.T.L. Wang, Kunpeng Zhang, K. Jeong, D. Shasha
{"title":"A tool for tree pattern matching","authors":"J.T.L. Wang, Kunpeng Zhang, K. Jeong, D. Shasha","doi":"10.1109/TAI.1991.167125","DOIUrl":"https://doi.org/10.1109/TAI.1991.167125","url":null,"abstract":"A description is presented of a system, called approximate-tree-by-example (ATBE), which supports AI applications that involve comparing ordered labeled trees or retrieving/extracting information from repositories of such trees. The ATBE system interacts with users through a powerful query language; graphical devices are provided to facilitate inputting the queries. The system is designed to be extensible, customizable, and portable, which makes it a very useful tool for tree pattern matching in various environments. The use of the tool is illustrated. Several examples taken directly from the complete implementation are discussed.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134373354","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
Experience-based deductive learning 基于经验的演绎学习
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167033
Joongmin Choi, S. Shapiro
{"title":"Experience-based deductive learning","authors":"Joongmin Choi, S. Shapiro","doi":"10.1109/TAI.1991.167033","DOIUrl":"https://doi.org/10.1109/TAI.1991.167033","url":null,"abstract":"A method of deductive learning is proposed to control deductive inference. The goal is to improve problem solving time by experience, when that experience monotonically adds knowledge to the knowledge base. Accumulating and exploiting experience are done by the schemes of knowledge migration and knowledge shadowing. Knowledge migration generates specific (migrated) rules from general (migrating) rules and accumulates deduction experience represented by specificity relationships between migrating and migrated rules. Knowledge shadowing recognizes rule redundancies during a deduction and prunes deduction branches activated from redundant rules. Three principles for knowledge shadowing are suggested, depending on the details of deduction experience representation.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133601471","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: 8
A logic theory of learning from experience 从经验中学习的逻辑理论
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167052
Wei Li
{"title":"A logic theory of learning from experience","authors":"Wei Li","doi":"10.1109/TAI.1991.167052","DOIUrl":"https://doi.org/10.1109/TAI.1991.167052","url":null,"abstract":"A formal description is presented of the process learning from experience. First-order logic is used as a language to denote knowledge. The theory consists of a first-order logic in Gentzen style, two concepts of counterexample and refutation by facts, and a hypothesis calculus for modifying a theory to match the human's observation and experiments. A comparison with nonmonotonic logic is also made.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134119496","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
PLANET: A tool for representing and generating plans in an RMS framework PLANET:在RMS框架中表示和生成计划的工具
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167082
Jaidev, N. Parameswaran
{"title":"PLANET: A tool for representing and generating plans in an RMS framework","authors":"Jaidev, N. Parameswaran","doi":"10.1109/TAI.1991.167082","DOIUrl":"https://doi.org/10.1109/TAI.1991.167082","url":null,"abstract":"Realistic planning must be viewed as an iteration of plan search, explanation generation, and observation. A framework that provides an ideal representation for all these purposes is the reason maintenance system (RMS). In order to capture all aspects of planning, the RMS must be able to model the functionality of the heuristic layer, the plan layer, and the domain layer in the dependency network. A description is presented of PLANET, a tool that provides such a facility along with a set of planning primitives, with which a user can represent the plan logic, formulate plan strategies, and generate explanations within a RMS framework.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125942417","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 machine learning tool for computer aided molecular design 用于计算机辅助分子设计的机器学习工具
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167080
G. Bolis, L. Pace, Filippo Fabrocini
{"title":"A machine learning tool for computer aided molecular design","authors":"G. Bolis, L. Pace, Filippo Fabrocini","doi":"10.1109/TAI.1991.167080","DOIUrl":"https://doi.org/10.1109/TAI.1991.167080","url":null,"abstract":"A description is given of KAMD (knowledge-aided molecular design), a machine learning tool that helps biochemists to reduce the number of experiments needed for molecular or, drug design processes. A report is presented on experience in applying machine learning techniques to a complex real-world problem. In this context, dynamic bias management is presented as a critical mechanism to deal with complex problems that typically exhibit a large number of distinct disjuncts. A summary of KAMD results for the system of thermolysin enzyme inhibitors is presented and discussed.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127100364","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
On-line handwritten Kanji character recognition using hypothesis generation in the space of hierarchical knowledge 基于分层知识空间假设生成的在线手写体汉字字符识别
[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI: 10.1109/TAI.1991.167036
K. Ohmori, Y. Haruki
{"title":"On-line handwritten Kanji character recognition using hypothesis generation in the space of hierarchical knowledge","authors":"K. Ohmori, Y. Haruki","doi":"10.1109/TAI.1991.167036","DOIUrl":"https://doi.org/10.1109/TAI.1991.167036","url":null,"abstract":"For online handwritten Kanji recognition, a new approach that cyclically generates a more concrete hypothesis from the current hypothesis by using hierarchically represented knowledge and that has achieved high recognition rate in reduced processing time is described. The properties of a characteristic stroke are represented in the form of fuzzy rules. Characteristic strokes, each of which is close to part of an input pattern stroke, are found by fuzzy inference, where each input pattern stroke is investigated by using fuzzy rulers.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129618508","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
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