The architecture of an expert system model using artificial neural networks is proposed. The proposed model effectively supports the necessary components of an expert system such as user interface facility knowledge base, inference engine, and explanation system. The expert system model (ESM) consists of several orders of simple neural networks, each realizing a simple task. These simple neural networks are organized vertically, thereby achieving a second level of parallelism. A novel way to handle both forward and backward chaining reasoning mechanisms is presented. A secondary network model monitors the reasoning patterns of the primary model.<>
{"title":"A neural network based expert system model","authors":"A. Hudli, M. Palakal, M. J. Zoran","doi":"10.1109/TAI.1991.167089","DOIUrl":"https://doi.org/10.1109/TAI.1991.167089","url":null,"abstract":"The architecture of an expert system model using artificial neural networks is proposed. The proposed model effectively supports the necessary components of an expert system such as user interface facility knowledge base, inference engine, and explanation system. The expert system model (ESM) consists of several orders of simple neural networks, each realizing a simple task. These simple neural networks are organized vertically, thereby achieving a second level of parallelism. A novel way to handle both forward and backward chaining reasoning mechanisms is presented. A secondary network model monitors the reasoning patterns of the primary model.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"662 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":"121998742","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 problem of distinguishing shapes from a compound contour, which is formed by overlapping more than one distinct object, is considered. The algorithm exploits the fact that planar shapes can be completely described by contour segments, and that they can be decomposed at their maximum concavity into simpler objects. To reduce spurious decomposition, the decomposed segments are merged hypotheses. The algorithm calculates the linking possibility by weighting the angular differentiation which measures against k-curvature consistency. The techniques were implemented and applied to other partial shape matching problems for clustering purposes.<>
{"title":"Automatic contour segmentation for object analysis","authors":"D. Hung, I. Chen","doi":"10.1109/TAI.1991.167041","DOIUrl":"https://doi.org/10.1109/TAI.1991.167041","url":null,"abstract":"The problem of distinguishing shapes from a compound contour, which is formed by overlapping more than one distinct object, is considered. The algorithm exploits the fact that planar shapes can be completely described by contour segments, and that they can be decomposed at their maximum concavity into simpler objects. To reduce spurious decomposition, the decomposed segments are merged hypotheses. The algorithm calculates the linking possibility by weighting the angular differentiation which measures against k-curvature consistency. The techniques were implemented and applied to other partial shape matching problems for clustering purposes.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"513 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":"123249131","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 principle of optimal information distribution is a criterion for the efficient use of the different information storage resources in a given network. Furthermore, it can be used as a tool to balance the system parameters and to obtain the optimal network parameter configuration according to the minimal system storage (system description information) for a given maximal performance error. The principle was derived by maximizing the output information of the network. The use of the principle was demonstrated for the example of a simple nonlinear function approximation.<>
{"title":"The determination of neural network parameters by information theory","authors":"R. Brause","doi":"10.1109/TAI.1991.167110","DOIUrl":"https://doi.org/10.1109/TAI.1991.167110","url":null,"abstract":"The principle of optimal information distribution is a criterion for the efficient use of the different information storage resources in a given network. Furthermore, it can be used as a tool to balance the system parameters and to obtain the optimal network parameter configuration according to the minimal system storage (system description information) for a given maximal performance error. The principle was derived by maximizing the output information of the network. The use of the principle was demonstrated for the example of a simple nonlinear function approximation.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"25 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":"130606683","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}
Most real-time planning algorithms address either the issue of response-time constraints or the issue of dynamic environments. A new real-time planning algorithm, DYNORA, is proposed to address both of these issues simultaneously. DYNORA is structured as a sequence of partial planning and execution cycles to avoid obsolescence of planning solutions at the time of execution. DYNORA uses a stopping criterion to balance planning cost and execution cost to achieve near optimal response times. DYNORA was used for the routing problem to optimize total cost. It shows better average-case time complexity than traditional real-time algorithms.<>
{"title":"DYNORA: a real-time planning algorithm to meet response-time constraints in dynamic environments","authors":"B. Hamidzadeh, S. Shekhar","doi":"10.1109/TAI.1991.167099","DOIUrl":"https://doi.org/10.1109/TAI.1991.167099","url":null,"abstract":"Most real-time planning algorithms address either the issue of response-time constraints or the issue of dynamic environments. A new real-time planning algorithm, DYNORA, is proposed to address both of these issues simultaneously. DYNORA is structured as a sequence of partial planning and execution cycles to avoid obsolescence of planning solutions at the time of execution. DYNORA uses a stopping criterion to balance planning cost and execution cost to achieve near optimal response times. DYNORA was used for the routing problem to optimize total cost. It shows better average-case time complexity than traditional real-time algorithms.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"13 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":"125826996","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 new temporal representation combining the notions of intervals, dates, and durations is presented. The manipulation of this representation is based on the notion of time map managers (TMMs) allowing both kinds of constraints, symbolic or numeric. These algorithms are a generalization of AC4, an optimal algorithm for arc-consistency, and can handle n-ary constraints.<>
{"title":"Representing and propagating constraints in temporal reasoning","authors":"H. Tolba, F. Charpillet, J. Haton","doi":"10.1109/TAI.1991.167093","DOIUrl":"https://doi.org/10.1109/TAI.1991.167093","url":null,"abstract":"A new temporal representation combining the notions of intervals, dates, and durations is presented. The manipulation of this representation is based on the notion of time map managers (TMMs) allowing both kinds of constraints, symbolic or numeric. These algorithms are a generalization of AC4, an optimal algorithm for arc-consistency, and can handle n-ary constraints.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122034124","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：