We propose a new method to mine a type scheme semi-automatically from an initial database scheme and the instances. Our data model assumes that one entity may have more than one type and classification (or type scheme). It might be appropriate when each entity is classified into at most k (least general) classes with respect to the ISA hierarchy, to keep database processing efficient. Our method differs from others in evolving ISA hierarchy by introducing a semantical metric. We propose a sophisticated algorithm to simplify, evolve and generate type schemes.
{"title":"Knowledge acquisition for classification systems","authors":"T. Miura, I. Shioya","doi":"10.1109/TAI.1996.560438","DOIUrl":"https://doi.org/10.1109/TAI.1996.560438","url":null,"abstract":"We propose a new method to mine a type scheme semi-automatically from an initial database scheme and the instances. Our data model assumes that one entity may have more than one type and classification (or type scheme). It might be appropriate when each entity is classified into at most k (least general) classes with respect to the ISA hierarchy, to keep database processing efficient. Our method differs from others in evolving ISA hierarchy by introducing a semantical metric. We propose a sophisticated algorithm to simplify, evolve and generate type schemes.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130435851","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}
Summary form only given. We perceive objects in the world as meaningful entities only over certain ranges of scale. This fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. In their seminal works, Witkin (1983) and Koenderink (1984) proposed to approach this problem by representing image structures at different scales in a so-called scale-space representation. Traditional scale-space theory building on this work, however, does not address the problem of how to select local appropriate scales for further analysis. After a brief review of the main ideas behind a scale-space representation, I describe a systematic methodology for generating hypotheses about interesting scale levels in image data based on a general principle stating that local extrema over scales of different combinations of normalized derivatives are likely candidates to correspond to interesting image structures. Specifically, I show how this idea can be used for formulating feature detectors which automatically adapt their local scales of processing to the local image structure. I show how the scale selection approach applies to various types of feature detection problems in early vision. In many computer vision applications, the poor performance of the low-level vision modules constitutes a major bottleneck.
{"title":"Automatic scale selection as a pre-processing stage to interpreting real-world data","authors":"T. Lindeberg","doi":"10.1109/TAI.1996.560799","DOIUrl":"https://doi.org/10.1109/TAI.1996.560799","url":null,"abstract":"Summary form only given. We perceive objects in the world as meaningful entities only over certain ranges of scale. This fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. In their seminal works, Witkin (1983) and Koenderink (1984) proposed to approach this problem by representing image structures at different scales in a so-called scale-space representation. Traditional scale-space theory building on this work, however, does not address the problem of how to select local appropriate scales for further analysis. After a brief review of the main ideas behind a scale-space representation, I describe a systematic methodology for generating hypotheses about interesting scale levels in image data based on a general principle stating that local extrema over scales of different combinations of normalized derivatives are likely candidates to correspond to interesting image structures. Specifically, I show how this idea can be used for formulating feature detectors which automatically adapt their local scales of processing to the local image structure. I show how the scale selection approach applies to various types of feature detection problems in early vision. In many computer vision applications, the poor performance of the low-level vision modules constitutes a major bottleneck.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114716846","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}
In previous work (J.-M. Gallone and F. Charpillet, 1996), we have studied the Hopfield artificial neural network model and its use for solving a particular scheduling problem: non preemptive tasks with release times, deadlines and computation times to be scheduled on several uniform machines. We presented an iterative approach based on Hopfield networks which enables resource bounded reasoning. We have validated our approach on a great number of randomly generated examples. Results are better than an efficient scheduling heuristics when no timing constraint exists and our system is able to adapt its behavior when timing constraints are imposed by the application. We extend this work by studying the incidence of two kinds of approximations on the processing time and on the success rate, so as to decide what sequence of activations for the contract will be likely to give the best success rate.
{"title":"Composing approximated algorithms based on Hopfield neural network for building a resource-bounded scheduler","authors":"J. Gallone, F. Charpillet","doi":"10.1109/TAI.1996.560776","DOIUrl":"https://doi.org/10.1109/TAI.1996.560776","url":null,"abstract":"In previous work (J.-M. Gallone and F. Charpillet, 1996), we have studied the Hopfield artificial neural network model and its use for solving a particular scheduling problem: non preemptive tasks with release times, deadlines and computation times to be scheduled on several uniform machines. We presented an iterative approach based on Hopfield networks which enables resource bounded reasoning. We have validated our approach on a great number of randomly generated examples. Results are better than an efficient scheduling heuristics when no timing constraint exists and our system is able to adapt its behavior when timing constraints are imposed by the application. We extend this work by studying the incidence of two kinds of approximations on the processing time and on the success rate, so as to decide what sequence of activations for the contract will be likely to give the best success rate.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128518260","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}
The recognition of temporal scenarios is expressed by means of the proximity between a scenario (which represents a system's possible behavior) and a session (which describes the observed behaviour). This recognition is qualified with a proximity index, which allows one to classify, either online or offline, the scenario candidates for an explanation of the evolution. This approach, when used in a dynamic system's supervisory or diagnostic tasks, opens up possibilities for using or learning scenarios, or even for structuring the scenarios.
{"title":"Recognising a scenario by calculating a temporal proximity index between constraint graphs","authors":"Nicolas Ramaux, D. Fontaine","doi":"10.1109/TAI.1996.560788","DOIUrl":"https://doi.org/10.1109/TAI.1996.560788","url":null,"abstract":"The recognition of temporal scenarios is expressed by means of the proximity between a scenario (which represents a system's possible behavior) and a session (which describes the observed behaviour). This recognition is qualified with a proximity index, which allows one to classify, either online or offline, the scenario candidates for an explanation of the evolution. This approach, when used in a dynamic system's supervisory or diagnostic tasks, opens up possibilities for using or learning scenarios, or even for structuring the scenarios.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132501501","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}
There is a need to develop more intelligent means for handling text in applications such as information retrieval, information filtering, and message classification. This raises the need for mechanisms for ascertaining what an item of text is about. Even though natural language processing offers the best results, it is not always viable. A less accurate, but more viable alternative, is to reason with keywords in the text. Unfortunately, classical reasoning is often inadequate for determining from some keywords what a text is about. In particular it does not allow context-dependent interpretation of keywords. So for example, if some text has the keyword oil, it is usually also about minerals, though with exceptions such as when it has the keyword cooling. To address this kind of problem, we consider a model of "aboutness" based on default logic.
{"title":"Intelligent text handling using default logic","authors":"A. Hunter","doi":"10.1109/TAI.1996.560397","DOIUrl":"https://doi.org/10.1109/TAI.1996.560397","url":null,"abstract":"There is a need to develop more intelligent means for handling text in applications such as information retrieval, information filtering, and message classification. This raises the need for mechanisms for ascertaining what an item of text is about. Even though natural language processing offers the best results, it is not always viable. A less accurate, but more viable alternative, is to reason with keywords in the text. Unfortunately, classical reasoning is often inadequate for determining from some keywords what a text is about. In particular it does not allow context-dependent interpretation of keywords. So for example, if some text has the keyword oil, it is usually also about minerals, though with exceptions such as when it has the keyword cooling. To address this kind of problem, we consider a model of \"aboutness\" based on default logic.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"329 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123394879","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}
Contextual reasoning has been proposed as a tool for solving the problem of generality in AI and for effectively handling huge knowledge bases, while approximate reasoning has been developed to overcome the computational barrier of classical deduction. This paper combines these approaches to provide an intuitive representation of knowledge and an effective deduction. Its semantics and a tableau calculus are presented. The key computational features are discussed.
{"title":"Approximate reasoning for contextual databases","authors":"F. Massacci","doi":"10.1109/TAI.1996.560468","DOIUrl":"https://doi.org/10.1109/TAI.1996.560468","url":null,"abstract":"Contextual reasoning has been proposed as a tool for solving the problem of generality in AI and for effectively handling huge knowledge bases, while approximate reasoning has been developed to overcome the computational barrier of classical deduction. This paper combines these approaches to provide an intuitive representation of knowledge and an effective deduction. Its semantics and a tableau calculus are presented. The key computational features are discussed.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125712889","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}
We propose a general approach for reasoning in space. The approach is composed of a set of two general constraints to govern the spatial relationships between objects in space, and two rules to propagate relationships between those objects. The approach is based on a uniform representation of the topology of the space as a connected set of components using a structure called adjacency matrix which can capture the topology of objects of different complexity in any space dimension. The relationships between objects are represented by the intersection of the space components. The approach is also shown to be applicable to reasoning in the temporal domain and is used to explain the conceptual neighbourhood phenomenon related to the reasoning process. A major advantage of the method is that reasoning between objects of any complexity can be achieved in a defined limited number of steps. Hence, the incorporation of spatial reasoning mechanisms in spatial information systems becomes possible.
{"title":"Order in space: a general formalism for spatial reasoning","authors":"B. El-Geresy, A. Abdelmoty","doi":"10.1109/TAI.1996.560450","DOIUrl":"https://doi.org/10.1109/TAI.1996.560450","url":null,"abstract":"We propose a general approach for reasoning in space. The approach is composed of a set of two general constraints to govern the spatial relationships between objects in space, and two rules to propagate relationships between those objects. The approach is based on a uniform representation of the topology of the space as a connected set of components using a structure called adjacency matrix which can capture the topology of objects of different complexity in any space dimension. The relationships between objects are represented by the intersection of the space components. The approach is also shown to be applicable to reasoning in the temporal domain and is used to explain the conceptual neighbourhood phenomenon related to the reasoning process. A major advantage of the method is that reasoning between objects of any complexity can be achieved in a defined limited number of steps. Hence, the incorporation of spatial reasoning mechanisms in spatial information systems becomes possible.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124980979","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}
A neural network construction method for problems specified for data sets with input and/or output values in the continuous or discrete domain is described and evaluated. This approach is based on a Boolean approximation of the data set and is generic for various neural network architectures. The construction method takes advantage of a construction method for Boolean problems without increasing the dimensions of the input or output vectors, which is an advantage over approaches which work on a binarized version of the data set with an increased number of input and output elements. Further, the networks are pruned in a second phase in order to obtain very small networks.
{"title":"A Boolean approach to construct neural networks for non-Boolean problems","authors":"G. Thimm, E. Fiesler","doi":"10.1109/TAI.1996.560784","DOIUrl":"https://doi.org/10.1109/TAI.1996.560784","url":null,"abstract":"A neural network construction method for problems specified for data sets with input and/or output values in the continuous or discrete domain is described and evaluated. This approach is based on a Boolean approximation of the data set and is generic for various neural network architectures. The construction method takes advantage of a construction method for Boolean problems without increasing the dimensions of the input or output vectors, which is an advantage over approaches which work on a binarized version of the data set with an increased number of input and output elements. Further, the networks are pruned in a second phase in order to obtain very small networks.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132598668","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}
The paper presents the TASK framework which is intended to cover the life cycle of a knowledge based system. TASK provides: (i) a conceptual language which enables an informal specification at the knowledge level; (ii) a formal language TFL which permits an unambiguous specification; and (iii) an operational shell TASK/sup +/ which allows an efficient execution even for badly structured problems. The paper presents the different languages, the links between them and emphasizes the implementation stage. We show how TASK proposes a nice compromise solution between efficiency and expressivity.
{"title":"TASK: from the specification to the implementation","authors":"Xavier Talon, C. Golbreich","doi":"10.1109/TAI.1996.560404","DOIUrl":"https://doi.org/10.1109/TAI.1996.560404","url":null,"abstract":"The paper presents the TASK framework which is intended to cover the life cycle of a knowledge based system. TASK provides: (i) a conceptual language which enables an informal specification at the knowledge level; (ii) a formal language TFL which permits an unambiguous specification; and (iii) an operational shell TASK/sup +/ which allows an efficient execution even for badly structured problems. The paper presents the different languages, the links between them and emphasizes the implementation stage. We show how TASK proposes a nice compromise solution between efficiency and expressivity.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133918928","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}
A modelling technique, using recurrent networks, based on the NARMAX framework (Nonlinear Autoregressive Moving Average with Exogenous Inputs), is developed. Some properties of the technique are demonstrated by means of a mathematical example. In the NARMAX model, the term N indicates that the model is based on nonlinear equations, AR indicates that previous observations (y) are used, MA indicates that previous errors (e) are used and X indicates that exogenous inputs (u) are used. Often, the number of delay lines on each input type is mentioned together with the type of model. The proposed solution to the delay length problem is to use a fully recurrent neural network with the RTRL algorithm (R.J. Williams and D. Zipser, 1989) as learning scheme.
基于NARMAX框架(带外生输入的非线性自回归移动平均)，开发了一种使用循环网络的建模技术。通过一个数学实例证明了该方法的一些性质。在NARMAX模型中，N项表示模型基于非线性方程，AR表示使用以前的观测值(y)， MA表示使用以前的误差(e)， X表示使用外源输入(u)。通常，每种输入类型上的延迟线数量与模型类型一起提到。提出的延迟长度问题的解决方案是使用RTRL算法(R.J. Williams and D. Zipser, 1989)作为学习方案的全递归神经网络。
{"title":"Implementing empirical modelling techniques with recurrent neural networks","authors":"T. Catfolis, K. Meert","doi":"10.1109/TAI.1996.560746","DOIUrl":"https://doi.org/10.1109/TAI.1996.560746","url":null,"abstract":"A modelling technique, using recurrent networks, based on the NARMAX framework (Nonlinear Autoregressive Moving Average with Exogenous Inputs), is developed. Some properties of the technique are demonstrated by means of a mathematical example. In the NARMAX model, the term N indicates that the model is based on nonlinear equations, AR indicates that previous observations (y) are used, MA indicates that previous errors (e) are used and X indicates that exogenous inputs (u) are used. Often, the number of delay lines on each input type is mentioned together with the type of model. The proposed solution to the delay length problem is to use a fully recurrent neural network with the RTRL algorithm (R.J. Williams and D. Zipser, 1989) as learning scheme.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134438958","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：