发布求助
文献互助 智能选刊 最新文献

Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94最新文献

筛选
英文 中文
An interactive train scheduling workbench based on artificial intelligence 基于人工智能的交互式列车调度工作台
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346515
Hsien-Cheng Lin, Ching-Chi Hsu
{"title":"An interactive train scheduling workbench based on artificial intelligence","authors":"Hsien-Cheng Lin, Ching-Chi Hsu","doi":"10.1109/TAI.1994.346515","DOIUrl":"https://doi.org/10.1109/TAI.1994.346515","url":null,"abstract":"We describe a practical train scheduling system (called TSS) designed for the Taiwan Railway Bureau (TRB). TSS has two major components. The first is Auto Scheduler which includes an initial scheduler, a conflict finder, and a conflict resolver. Auto Scheduler uses the concept of bugging as problem solving tactics. The second is Manual Scheduler which provides some effective editing functions for users to tune schedules generated by Auto Scheduler. Through an easy-to-use user interface, these components can be used to solve large-scale complex train scheduling problems.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117254448","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 evolution of intelligent writing assistants: trends and future prospects 智能写作助手的演变:趋势与未来展望
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346488
R. Oakman
{"title":"The evolution of intelligent writing assistants: trends and future prospects","authors":"R. Oakman","doi":"10.1109/TAI.1994.346488","DOIUrl":"https://doi.org/10.1109/TAI.1994.346488","url":null,"abstract":"Since Writer's Workbench (Bell Telephone Laboratories, early 1980's), software for writing assistance and style checking has evolved over the last decade (1984-94) to become more intelligent and interactive. During this period the author has been involved in the development of several software packages and has monitored the growth and sophistication of software solutions. Today certain characteristics have become standard; yet challenges remain. The author discusses trends and suggests areas where we might expect continued future development. Today writers have a variety of useful but limited style and grammar checkers available for most computer systems. Some even come bundled with the current generation of enhanced word processors and are used by many writers. Another approach to writing assistance is suggested by online interactive group writing systems like MediaLink. Possibilities for combining the best features of current systems exist, but further improvements in the quality of the knowledge offered by automated writing assistants will depend on research advances in other areas of natural language processing. The author examines some of these problem areas and suggests approaches from ongoing NLP research that we can expect the writing assistants and style checkers of the future to include among their resources.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127152375","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
Experiments with various recurrent neural network architectures for handwritten character recognition 手写体字符识别的各种递归神经网络体系结构实验
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346444
A. Jameel
{"title":"Experiments with various recurrent neural network architectures for handwritten character recognition","authors":"A. Jameel","doi":"10.1109/TAI.1994.346444","DOIUrl":"https://doi.org/10.1109/TAI.1994.346444","url":null,"abstract":"This paper reports evaluations of several neural architectures when the handwritten character recognition is approached as a problem of spectro-temporal pattern recognition. In general, neural networks specialize in learning either the spectral or temporal characteristics of patterns. However, choice of appropriate features and architectures could lead to obtaining both spectral and temporal characteristics from the handwritten character patterns. One such feature and three appropriate architectures are the focus of this paper. The results obtained during a limited set of experiments indicate a great potential for the spectro-temporal approach to be a useful contender for being a part of schemes of handwritten character recognition systems. In addition, a simple voting method is presented for collaborative character recognition using three different recognition criteria.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124818123","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
Text-based systems and information management: artificial intelligence confronts matters of scale 基于文本的系统和信息管理:人工智能面临着规模问题
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346487
P. Jacobs
{"title":"Text-based systems and information management: artificial intelligence confronts matters of scale","authors":"P. Jacobs","doi":"10.1109/TAI.1994.346487","DOIUrl":"https://doi.org/10.1109/TAI.1994.346487","url":null,"abstract":"Many of the more ambitious goals of artificial intelligence have proved unattainable because of the failure of the many small, successful systems to scale up. The general use of technologies such as natural language interfaces and expert systems has done little to alleviate the basic difficulties and overwhelming cost of knowledge engineering. At the same time, emerging text processing techniques, including data extraction from text and new text retrieval methods, offer a means of accessing stores of information many times larger than any organized knowledge base or database. Although knowledge acquisition from text is at the heart of the information management problem, interpreting text, paradoxically, requires large amounts of knowledge, mainly about the way words are used in context. In other words, before intelligent text processing systems can be trained to mine for useful knowledge, they must already have enough knowledge to interpret what they read. The point at which there is \"enough\", is still a matter of debate, as no real program seems close to having enough knowledge to achieve general human-like understanding. Current research in large-scale natural language processing has come, rightly, to focus on lexical acquisition as the key to future progress. Unfortunately, the current state of the art is quite far from the recipe for acquiring knowledge about words, because it leans too heavily on resources that are available, without consideration for what is needed.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124857426","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
Using a double-based genetic algorithm on a population of computer programs 在一组计算机程序中使用双基遗传算法
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346462
P. Collard, J.-L. Segapeli
{"title":"Using a double-based genetic algorithm on a population of computer programs","authors":"P. Collard, J.-L. Segapeli","doi":"10.1109/TAI.1994.346462","DOIUrl":"https://doi.org/10.1109/TAI.1994.346462","url":null,"abstract":"In this paper, we present a new approach, which improves the performance of a genetic algorithm. Genetic algorithms are iterative search procedures based on natural genetic. We use an original genetic algorithm that manipulates pairs of twins in its population: DGA, double-based genetic algorithm. We show that this approach is relevant for genetic programming, which manipulates populations of trees. In particular, we show that doubles enable to transform a deceptive problem into a convergent one. We also prove that using pairs of double functions in the primitive function set is more efficient in the problem of learning boolean functions.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125359381","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
Natural language processing tools and environments: the field in perspective 自然语言处理工具和环境:透视领域
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346491
B. Manaris
{"title":"Natural language processing tools and environments: the field in perspective","authors":"B. Manaris","doi":"10.1109/TAI.1994.346491","DOIUrl":"https://doi.org/10.1109/TAI.1994.346491","url":null,"abstract":"Tools and environments for natural language processing (NLP) originated approximately four decades ago with dictionary-based machine translation systems. When examining the evolution of the field, one observes a transition from these \"embryonic\" systems of the fifties to the more adaptable, robust, and user-friendly environments of the nineties. Currently, the state-of-the-art in such systems is based on a wide variety of linguistic theories, cognitive models, and engineering approaches. The paper looks briefly at the tools and environments available today.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"227 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122347543","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
Towards the integration of artificial neural networks and constraint logic programming 人工神经网络与约束逻辑规划的融合
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346458
Jimmy Ho-man Lee, V. Tam
{"title":"Towards the integration of artificial neural networks and constraint logic programming","authors":"Jimmy Ho-man Lee, V. Tam","doi":"10.1109/TAI.1994.346458","DOIUrl":"https://doi.org/10.1109/TAI.1994.346458","url":null,"abstract":"We present a general framework for integrating artificial neural networks (ANN) into constraint logic programming for solving constraint satisfaction problems (CSPs). This framework is realized in a novel programming language PROCLANN, which uses the standard goal reduction strategy as frontend to generate constraints for an efficient backend ANN-based constraint-solver. PROCLANN retains the simple and elegant declarative semantics of constraint logic programming. Its operational semantics is probabilistic in nature but it possesses soundness and completeness results. An initial prototype of PROCLANN is constructed and provides empirical evidence that PROCLANN compares favourably against the state of art in CLP implementations on certain hard instances of CSP.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122116182","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
A knowledge-based analyzer for requirements specification analysis 用于需求规范分析的基于知识的分析器
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346480
Hung-Chin Jang
{"title":"A knowledge-based analyzer for requirements specification analysis","authors":"Hung-Chin Jang","doi":"10.1109/TAI.1994.346480","DOIUrl":"https://doi.org/10.1109/TAI.1994.346480","url":null,"abstract":"In this paper, we propose a knowledge-based analyzer of a formal requirements specification language RT-FRORL for requirements specification analysis. The RT-FRORL analyzer is based on an underlying verification framework and associated verification methodologies. The framework originates from an integration of rapid prototyping, operational specification, and transformational implementation. The verification methodologies consist of a combination of resolution refutation, anomaly detection matrix, and algorithms methods. A RT-FRORL system analyzer was implemented using Arity/Prolog and Turbo C languages on 80486-33 PC.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129739927","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 new arc consistency algorithm for CSPs with hierarchical domains 一种新的分层域csp的弧一致性算法
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346459
T. Kokeny
{"title":"A new arc consistency algorithm for CSPs with hierarchical domains","authors":"T. Kokeny","doi":"10.1109/TAI.1994.346459","DOIUrl":"https://doi.org/10.1109/TAI.1994.346459","url":null,"abstract":"General arc-consistency filtering techniques for constraint satisfaction problems (CSP) can be improved by considering special CSP classes. A domain hierarchical CSP is a CSP in which an intrinsic hierarchical structure of its domains is known. A.K. Mackworth et al. (1985) proposed an are consistency algorithm for domain hierarchical CSPs (HAC) whose worst-case time complexity was 0(md/sup 3/) where m is the number of constraints and d is the maximal size of a domain. HAC worked only with binary tree structured domains. In this paper we present HAC-6 a new arc-consistency algorithm for domain hierarchical CSPs which works with all types of domain hierarchies (any partial ordering) and its worst-case complexity is 0(md/sup 2/). HAC-6 is based on AC-6 which is the best at present, worst-case optimal arc-consistency algorithm for classical CSPs.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130565547","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
Recurrent neural networks for synthesizing linear control systems via pole placement 用递归神经网络通过极点放置来综合线性控制系统
Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94 Pub Date : 1994-11-06 DOI: 10.1109/TAI.1994.346472
Jun Wang, Guanghua Wu
{"title":"Recurrent neural networks for synthesizing linear control systems via pole placement","authors":"Jun Wang, Guanghua Wu","doi":"10.1109/TAI.1994.346472","DOIUrl":"https://doi.org/10.1109/TAI.1994.346472","url":null,"abstract":"Recurrent neural networks are proposed for synthesizing linear control systems through pole placement. The proposed neural networks approach uses two coupled recurrent neural networks for computing feedback gain matrix. Each neural network consists of two bidirectionally connected layers and each layer consists of an array of neurons. The proposed recurrent neural networks are shown to be capable of synthesizing linear control systems in real time. The operating characteristics of the recurrent neural networks and closed-loop systems are demonstrated by use of two illustrative examples.<<ETX>>","PeriodicalId":262014,"journal":{"name":"Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123680445","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
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：604180095
Book学术官方微信