A novel cooperative computation model, Cellula, is proposed, with particular attention given to group organisation and inter-/intragroup communication. This model is designed on two principles. First, it has a facility for abstraction of group behaviors, which makes it possible to cope with recursive problem decomposition. Second, it has a facility (based on blackboard communication) for inter-/intragroup communication necessary for the several types of group organization.<>
{"title":"A cooperation and communication framework for distributed problem solving","authors":"N. Yoshida, S. Narazaki","doi":"10.1109/TAI.1990.130393","DOIUrl":"https://doi.org/10.1109/TAI.1990.130393","url":null,"abstract":"A novel cooperative computation model, Cellula, is proposed, with particular attention given to group organisation and inter-/intragroup communication. This model is designed on two principles. First, it has a facility for abstraction of group behaviors, which makes it possible to cope with recursive problem decomposition. Second, it has a facility (based on blackboard communication) for inter-/intragroup communication necessary for the several types of group organization.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127881947","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 knowledge-based architecture designed to connect and correlate autonomous disparate information sources is presented. The information sources being integrated come equipped with logical front-ends that build up only those parts of a virtual global schema which are needed to process local or global requests. The schema building and translation processes are driven by respective knowledge bases. The core of the architecture is a connecting tissue in the form of a distributed knowledge modeling platform, also referred to as distributed cooperative object management. The proposed architecture is intended for a broad spectrum of use, ranging from heterogeneous business applications to sophisticated design systems. It is expected that the architecture can be implemented on top of open distributed processing environments.<>
{"title":"Knowledge based architecture to integrate heterogeneous distributed information systems","authors":"P. Bernus, M. Papazoglou","doi":"10.1109/TAI.1990.130420","DOIUrl":"https://doi.org/10.1109/TAI.1990.130420","url":null,"abstract":"A knowledge-based architecture designed to connect and correlate autonomous disparate information sources is presented. The information sources being integrated come equipped with logical front-ends that build up only those parts of a virtual global schema which are needed to process local or global requests. The schema building and translation processes are driven by respective knowledge bases. The core of the architecture is a connecting tissue in the form of a distributed knowledge modeling platform, also referred to as distributed cooperative object management. The proposed architecture is intended for a broad spectrum of use, ranging from heterogeneous business applications to sophisticated design systems. It is expected that the architecture can be implemented on top of open distributed processing environments.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125465737","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 novel ergodic discretized learning automaton which is epsilon-optimal is introduced. It utilizes a novel estimator learning algorithm which is based on the recent history of the environmental responses and is able to operate in nonstationary stochastic environments. The proposed automaton achieves significantly higher performance than the classical reward-penalty ergodic schemes. Extensive simulation results indicate the superiority of the proposed scheme. Furthermore, it is proved that it is epsilon-optimal in every stochastic environment.<>
{"title":"Ergodic discretized estimator learning automata with high accuracy and high adaptation rate for nonstationary environments","authors":"A. Vasilakos, G. Papadimitriou","doi":"10.1109/TAI.1990.130342","DOIUrl":"https://doi.org/10.1109/TAI.1990.130342","url":null,"abstract":"A novel ergodic discretized learning automaton which is epsilon-optimal is introduced. It utilizes a novel estimator learning algorithm which is based on the recent history of the environmental responses and is able to operate in nonstationary stochastic environments. The proposed automaton achieves significantly higher performance than the classical reward-penalty ergodic schemes. Extensive simulation results indicate the superiority of the proposed scheme. Furthermore, it is proved that it is epsilon-optimal in every stochastic environment.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123265750","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}
It is shown that Prolog can serve as a multi-purpose language in an image management system. With sufficient support routines, Prolog: is interpretive, in order to give immediate response; is programmable, allowing users to compose commands; can update and query the image database; can be used for optimization and constraint rules; and can perform input/output and communications. The architecture of PROFIM is described. The necessary enhancements of Prolog for it to be widely used in image management systems are summarized.<>
{"title":"PROFIM: Prolog for image management","authors":"Shan Chi, Jie-Young Juang","doi":"10.1109/TAI.1990.130449","DOIUrl":"https://doi.org/10.1109/TAI.1990.130449","url":null,"abstract":"It is shown that Prolog can serve as a multi-purpose language in an image management system. With sufficient support routines, Prolog: is interpretive, in order to give immediate response; is programmable, allowing users to compose commands; can update and query the image database; can be used for optimization and constraint rules; and can perform input/output and communications. The architecture of PROFIM is described. The necessary enhancements of Prolog for it to be widely used in image management systems are summarized.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126620708","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 constraint-based system for automating the acquisition of problem-solving knowledge is described. The approach is novel in attempting to compile rules from the observation of constraint-based, relaxation-based problem solving. The system has three main components; a constraint-based problem solver, a rule-compiler and a rule-base problem solver. A relation consistency algorithm is the backbone of the constraint-based problem solver. One advantage of this method is that customized expert systems can be built by manipulating the problems used for learning. Experiments were performed to evaluate a prototype learning system and some extensions.<>
{"title":"Rule compilation from constraint-based problem solving","authors":"S. Subramanian, Eugene C. Freuder","doi":"10.1109/TAI.1990.130307","DOIUrl":"https://doi.org/10.1109/TAI.1990.130307","url":null,"abstract":"A constraint-based system for automating the acquisition of problem-solving knowledge is described. The approach is novel in attempting to compile rules from the observation of constraint-based, relaxation-based problem solving. The system has three main components; a constraint-based problem solver, a rule-compiler and a rule-base problem solver. A relation consistency algorithm is the backbone of the constraint-based problem solver. One advantage of this method is that customized expert systems can be built by manipulating the problems used for learning. Experiments were performed to evaluate a prototype learning system and some extensions.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121219786","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 novel programming paradigm for the control of a robot manipulator by learning the mapping between the Cartesian space and the joint space (inverse kinematic) is discussed. It is based on a neural network model of optimal mappings between two high-dimensional spaces introduced by T. Kohonen (1982). The author describes the approach and presents the optimal mapping, based on the principle of maximal information gain. Furthermore, the principal control error made by the learned mapping is evaluated for the example of the PUMA robot. By introducing an optimization principle for the distribution of information in the neural network, the optimal system parameters, including the number of neurons and the optimal position encoding resolutions, are derived.<>
{"title":"Optimal information distribution and performance in neighbourhood-conserving maps for robot control","authors":"R. Brause","doi":"10.1109/TAI.1990.130379","DOIUrl":"https://doi.org/10.1109/TAI.1990.130379","url":null,"abstract":"A novel programming paradigm for the control of a robot manipulator by learning the mapping between the Cartesian space and the joint space (inverse kinematic) is discussed. It is based on a neural network model of optimal mappings between two high-dimensional spaces introduced by T. Kohonen (1982). The author describes the approach and presents the optimal mapping, based on the principle of maximal information gain. Furthermore, the principal control error made by the learned mapping is evaluated for the example of the PUMA robot. By introducing an optimization principle for the distribution of information in the neural network, the optimal system parameters, including the number of neurons and the optimal position encoding resolutions, are derived.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114273199","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}
Both theoretical and empirical results are presented concerning W. Van de Velde's (1989, 1990) decision tree induction algorithm IDL. Contrary to a conjecture by Van de Velde, the algorithm does not always produce a topologically minimal tree. This is true both of IDL used as an incremental decision tree induction algorithm and of IDL used as a post-processor for trees generated by TDIDT. Experiments have been made on using IDL in post-processing trees produced by ID3. The test domains are exclusive-OR functions with irrelevant attributes. The results show that in this domain IDL removes efficiently the tests of irrelevant attributes from the trees. The computational complexity analysis of IDL is reviewed.<>
本文给出了W. Van de Velde(1989, 1990)决策树归纳算法IDL的理论和实证结果。与Van de Velde的猜想相反，该算法并不总是产生拓扑最小树。无论是作为增量决策树归纳算法的IDL，还是作为TDIDT生成的树的后处理器的IDL，都是如此。利用IDL对ID3生成的后处理树进行了试验。测试域是具有不相关属性的异或函数。结果表明，在该域中，IDL能够有效地去除树中不相关属性的测试。综述了IDL的计算复杂度分析。
{"title":"On inducing topologically minimal decision trees","authors":"Tapio Elomaa, Jyrki Kivinen","doi":"10.1109/TAI.1990.130432","DOIUrl":"https://doi.org/10.1109/TAI.1990.130432","url":null,"abstract":"Both theoretical and empirical results are presented concerning W. Van de Velde's (1989, 1990) decision tree induction algorithm IDL. Contrary to a conjecture by Van de Velde, the algorithm does not always produce a topologically minimal tree. This is true both of IDL used as an incremental decision tree induction algorithm and of IDL used as a post-processor for trees generated by TDIDT. Experiments have been made on using IDL in post-processing trees produced by ID3. The test domains are exclusive-OR functions with irrelevant attributes. The results show that in this domain IDL removes efficiently the tests of irrelevant attributes from the trees. The computational complexity analysis of IDL is reviewed.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125274443","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 parallel logic programming system which includes a precompiler, a compiler, and an execution system is presented. An annotated parallel language which is a parallel extension of Prolog is introduced. The techniques used in the precompile phase, such as abstract interpretation and the CAAP (compiling approach for exploiting AND-parallelism) scheme, are described. An optimized compiler, the RAP/LOP (restricted AND-parallelism and limited OR-parallelism) parallel execution model, and the execution system are presented.<>
{"title":"Design and implementation of a parallel logic programming system","authors":"H. Shouren, G. Yaoqing, Hwang Zhiyi, C. Yun-gui","doi":"10.1109/TAI.1990.130390","DOIUrl":"https://doi.org/10.1109/TAI.1990.130390","url":null,"abstract":"A parallel logic programming system which includes a precompiler, a compiler, and an execution system is presented. An annotated parallel language which is a parallel extension of Prolog is introduced. The techniques used in the precompile phase, such as abstract interpretation and the CAAP (compiling approach for exploiting AND-parallelism) scheme, are described. An optimized compiler, the RAP/LOP (restricted AND-parallelism and limited OR-parallelism) parallel execution model, and the execution system are presented.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125226336","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}
Aïda Batarekh, A. Preece, Anne Bennett, P. Grogono
The authors focus on the problems of specification of an expert system namely, what needs to be specified, what can be specified and how. Two distinct major roles for a software specification are identified: as a contract between parties involved in system development and as a blueprint for the design and implementation of the system. It is shown that these purposes require quite different specifications. The role of specification as a contract is taken by the problem specification, which essentially describes what system is to be built. The blueprint specification is complementary, and describes how the system is to be built, including a description of the knowledge to be used and a description of how to represent and reason with that knowledge.<>
{"title":"Specification of expert systems","authors":"Aïda Batarekh, A. Preece, Anne Bennett, P. Grogono","doi":"10.1109/TAI.1990.130317","DOIUrl":"https://doi.org/10.1109/TAI.1990.130317","url":null,"abstract":"The authors focus on the problems of specification of an expert system namely, what needs to be specified, what can be specified and how. Two distinct major roles for a software specification are identified: as a contract between parties involved in system development and as a blueprint for the design and implementation of the system. It is shown that these purposes require quite different specifications. The role of specification as a contract is taken by the problem specification, which essentially describes what system is to be built. The blueprint specification is complementary, and describes how the system is to be built, including a description of the knowledge to be used and a description of how to represent and reason with that knowledge.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121855798","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}
While optimizing scheduling problems such as the traveling salesman problem has been common practice in neural networks, solving planning problems such as the Tower-of-Hanoi (TOH) has been difficult in neural networks. The differences between the scheduling and planning problems are identified here from the neural network perspective, based on which an approach to solve planning problems with learning is proposed. In particular, the TOH is chosen as the target problem and represented as an array of neurons. A set of constraints derived from the TOH is formulated based on this representation. The system is designed to learn to generate legal moves. Learning legal moves is accomplished by generating illegal states and by measuring the legality of the states. Simulation results show that the system moves in a direction in which it learns legal moves for the TOH.<>
{"title":"A connectionist approach to learning legal moves in Tower-of-Hanoi","authors":"A. Sohn, J. Gaudiot","doi":"10.1109/TAI.1990.130364","DOIUrl":"https://doi.org/10.1109/TAI.1990.130364","url":null,"abstract":"While optimizing scheduling problems such as the traveling salesman problem has been common practice in neural networks, solving planning problems such as the Tower-of-Hanoi (TOH) has been difficult in neural networks. The differences between the scheduling and planning problems are identified here from the neural network perspective, based on which an approach to solve planning problems with learning is proposed. In particular, the TOH is chosen as the target problem and represented as an array of neurons. A set of constraints derived from the TOH is formulated based on this representation. The system is designed to learn to generate legal moves. Learning legal moves is accomplished by generating illegal states and by measuring the legality of the states. Simulation results show that the system moves in a direction in which it learns legal moves for the TOH.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131889027","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：