The authors propose a programming system that combines pattern matching of Prolog with a novel approach to logic and the control of resolution. A network of nodes and arcs together with a three-valued logic is used to indicate the connections between predicates and their consequents, and to express the flow from facts and propositions of a theory to its theorems. In this way, one can handle uncertainty and negation properly in this 'neural logic network.' A neural logic program consists of a specification of network fragments, labeled with predicates and arc weights, and they can be joined dynamically to form a tree of reasoning chains. The architecture of the neural logic computational model is left open and the authors do not intend the model to be interpreted literally as a physical architecture.<>
{"title":"Neural logic programming","authors":"T. J. Reynolds, H. Teh, B. Low","doi":"10.1109/TAI.1990.130385","DOIUrl":"https://doi.org/10.1109/TAI.1990.130385","url":null,"abstract":"The authors propose a programming system that combines pattern matching of Prolog with a novel approach to logic and the control of resolution. A network of nodes and arcs together with a three-valued logic is used to indicate the connections between predicates and their consequents, and to express the flow from facts and propositions of a theory to its theorems. In this way, one can handle uncertainty and negation properly in this 'neural logic network.' A neural logic program consists of a specification of network fragments, labeled with predicates and arc weights, and they can be joined dynamically to form a tree of reasoning chains. The architecture of the neural logic computational model is left open and the authors do not intend the model to be interpreted literally as a physical architecture.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"3 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":"133853251","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 importance of stratification to automatic program generation is considered. Stratification of the variables of a weak specification seems to hold promise in the determination of the variable type, as well as in providing guarantees concerning the consistency, completeness, and ambiguity (or lack thereof) of the requirements specification.<>
{"title":"On the application of stratification to requirement specifications","authors":"D. Cooke, A. Gates","doi":"10.1109/TAI.1990.130434","DOIUrl":"https://doi.org/10.1109/TAI.1990.130434","url":null,"abstract":"The importance of stratification to automatic program generation is considered. Stratification of the variables of a weak specification seems to hold promise in the determination of the variable type, as well as in providing guarantees concerning the consistency, completeness, and ambiguity (or lack thereof) of the requirements specification.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"18 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":"133857416","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}
SHOOD, an object-oriented model, in which every attribute is a relationship, is discussed. Vertical relationships structuring knowledge (e.g., specialization) and horizontal relationships linking pieces of knowledge (e.g., composition) are distinguished. Here, object hierarchies (vertical) and interobject links (horizontal) are treated equally. Often, only one of these aspects is fully developed. It is suggested that vertical and horizontal relationships can be the basis of an object knowledge representation system.<>
{"title":"Relationships in an object knowledge representation model","authors":"José Escamilla, Patrice Jean","doi":"10.1109/TAI.1990.130411","DOIUrl":"https://doi.org/10.1109/TAI.1990.130411","url":null,"abstract":"SHOOD, an object-oriented model, in which every attribute is a relationship, is discussed. Vertical relationships structuring knowledge (e.g., specialization) and horizontal relationships linking pieces of knowledge (e.g., composition) are distinguished. Here, object hierarchies (vertical) and interobject links (horizontal) are treated equally. Often, only one of these aspects is fully developed. It is suggested that vertical and horizontal relationships can be the basis of an object knowledge representation system.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"82 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114012109","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 hybrid knowledge representation technique is presented which is used as a basis of a requirement specification language FRORL, (frame-and-rule oriented requirements specification language). To easily represent the structure and behavior of a software system, the syntax of FRORL is based on the concepts of frames and production rules. The semantic interpretation of the FRORL language is defined using Horn-clause logic augmented with the concept of multiple inheritance. The completeness and soundness of the hybrid knowledge representation technique are proved. Based on the full machinery of Horn-clause logic, the FRORL specification modeling the world can be checked against the known constraints of a given domain, and the known facts pertaining to the software system.<>
{"title":"A hybrid knowledge representation as a basis of requirement specification and reasoning","authors":"J. Tsai, T. Weigert, Hung-Chin Jang","doi":"10.1109/TAI.1990.130312","DOIUrl":"https://doi.org/10.1109/TAI.1990.130312","url":null,"abstract":"A hybrid knowledge representation technique is presented which is used as a basis of a requirement specification language FRORL, (frame-and-rule oriented requirements specification language). To easily represent the structure and behavior of a software system, the syntax of FRORL is based on the concepts of frames and production rules. The semantic interpretation of the FRORL language is defined using Horn-clause logic augmented with the concept of multiple inheritance. The completeness and soundness of the hybrid knowledge representation technique are proved. Based on the full machinery of Horn-clause logic, the FRORL specification modeling the world can be checked against the known constraints of a given domain, and the known facts pertaining to the software system.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"92 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":"121078917","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 method for eliciting interactive rules from data with exceptions is described. This method consists of the following three steps: create a hypothesis set (rule candidates); remove exceptional data; and choose the appropriate hypothesis. For the knowledge elicitation procedure, a TMS (truth maintenance system) is useful in choosing an appropriate hypothesis and detecting exceptional data candidates. The advantage in using TMS is that rules can be incrementally elicited from the data. The validity of this method is evaluated using a simple system which elicits rules about chemical reactions from a practical chemical reaction database. A comparison of results for this method and a statistical method shows that it is more useful in eliciting interactive rules.<>
{"title":"Automatic elicitation of interactive rules from data with exceptions using TMS","authors":"T. Yamazaki","doi":"10.1109/TAI.1990.130316","DOIUrl":"https://doi.org/10.1109/TAI.1990.130316","url":null,"abstract":"A method for eliciting interactive rules from data with exceptions is described. This method consists of the following three steps: create a hypothesis set (rule candidates); remove exceptional data; and choose the appropriate hypothesis. For the knowledge elicitation procedure, a TMS (truth maintenance system) is useful in choosing an appropriate hypothesis and detecting exceptional data candidates. The advantage in using TMS is that rules can be incrementally elicited from the data. The validity of this method is evaluated using a simple system which elicits rules about chemical reactions from a practical chemical reaction database. A comparison of results for this method and a statistical method shows that it is more useful in eliciting interactive rules.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"199 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":"122551277","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 simulator, the neural shell was developed to simplify the design and use of neural networks. The neural shell is a prototyping environment which runs on workstations and additionally supports the execution of large neural-network simulations on Cray supercomputers. Descriptions are given of the Neural Shell Window, the configuration window, the graphics display window, file requirements and the self-documentation facility.<>
{"title":"The neural shell: a neural network simulation tool","authors":"S. Ahalt, P. Chen, Cheng-Tao Chou","doi":"10.1109/TAI.1990.130320","DOIUrl":"https://doi.org/10.1109/TAI.1990.130320","url":null,"abstract":"A neural network simulator, the neural shell was developed to simplify the design and use of neural networks. The neural shell is a prototyping environment which runs on workstations and additionally supports the execution of large neural-network simulations on Cray supercomputers. Descriptions are given of the Neural Shell Window, the configuration window, the graphics display window, file requirements and the self-documentation facility.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"19 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":"126191380","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}
KNOWBEL is a tool offering the knowledge representation language Telos and the logic programming system MRS for the development of an expert system. Telos is a tightly integrated hybrid knowledge representation scheme, offering facilities for structuring a knowledge base as well as an assertional sublanguage for expressing deductive rules and integrity constraints. Unlike Prolog, MRS provides facilities for customizing an expert system inference engine. The KNOWBEL architecture clearly separates the knowledge and implementation levels for a knowledge base and its associated operations. KNOWBEL also supports temporal reasoning, extensive constraint enforcement, and a user-friendly window-based interface.<>
{"title":"KNOWBEL: a hybrid expert system building tool","authors":"J. Mylopoulos, Huaiqing Wang, A. Kushniruk","doi":"10.1109/TAI.1990.130451","DOIUrl":"https://doi.org/10.1109/TAI.1990.130451","url":null,"abstract":"KNOWBEL is a tool offering the knowledge representation language Telos and the logic programming system MRS for the development of an expert system. Telos is a tightly integrated hybrid knowledge representation scheme, offering facilities for structuring a knowledge base as well as an assertional sublanguage for expressing deductive rules and integrity constraints. Unlike Prolog, MRS provides facilities for customizing an expert system inference engine. The KNOWBEL architecture clearly separates the knowledge and implementation levels for a knowledge base and its associated operations. KNOWBEL also supports temporal reasoning, extensive constraint enforcement, and a user-friendly window-based interface.<<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":"125215150","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 discussion is given on a knowledge-based approach to the representation and implementation of the similarity evaluation of colors; all the aspects involved in color description and the relationships between color descriptions and similarity judgments may be explicitly represented in a quantitative, rigorous and reliable way. The authors choose CIELUV, which provides a flexible and powerful numerical description of color appearance, as the color description space and fuzzy logic as the knowledge representation language for modelling human judgments in the universe of discourse of CIELUV measures. An explanatory example of color image retrieval based on similarity measure is provided to aid the presentation of tools and strategies of the knowledge-based environment.<>
{"title":"A knowledge-based environment for assessment of color similarity","authors":"E. Binaghi, A. Ventura, A. Rampini, R. Schettini","doi":"10.1109/TAI.1990.130436","DOIUrl":"https://doi.org/10.1109/TAI.1990.130436","url":null,"abstract":"A discussion is given on a knowledge-based approach to the representation and implementation of the similarity evaluation of colors; all the aspects involved in color description and the relationships between color descriptions and similarity judgments may be explicitly represented in a quantitative, rigorous and reliable way. The authors choose CIELUV, which provides a flexible and powerful numerical description of color appearance, as the color description space and fuzzy logic as the knowledge representation language for modelling human judgments in the universe of discourse of CIELUV measures. An explanatory example of color image retrieval based on similarity measure is provided to aid the presentation of tools and strategies of the knowledge-based environment.<<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":"126407381","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 graphic description tool (KGDT) that is used to recognize and understand engineering drawings is described. This tool basically consists of a concept description network, a graphic description language, a physical description framework, a set of image processing modules, a matcher, a rule-based inference engine, an interpreter, and a blackboard control architecture. The matcher recognizes all graphic symbols and characters in the engineering drawing based on the various properties of the different graphic symbols and characters that are extracted by the low-level image processing routines. The rule-based inference engine is built to infer possible relations among graphic symbols and generate a relational graph. The interpreter is used to generate an acceptable explanation in terms of traversal of the relational graph. The interactions among the interpreter, the matcher, the inference engine, and the image processing routines are controlled by the blackboard control architecture.<>
{"title":"A knowledge-based graphic description tool for understanding engineering drawings","authors":"Yong-Qing Cheng, Jing-Yu Yang","doi":"10.1109/TAI.1990.130439","DOIUrl":"https://doi.org/10.1109/TAI.1990.130439","url":null,"abstract":"A knowledge-based graphic description tool (KGDT) that is used to recognize and understand engineering drawings is described. This tool basically consists of a concept description network, a graphic description language, a physical description framework, a set of image processing modules, a matcher, a rule-based inference engine, an interpreter, and a blackboard control architecture. The matcher recognizes all graphic symbols and characters in the engineering drawing based on the various properties of the different graphic symbols and characters that are extracted by the low-level image processing routines. The rule-based inference engine is built to infer possible relations among graphic symbols and generate a relational graph. The interpreter is used to generate an acceptable explanation in terms of traversal of the relational graph. The interactions among the interpreter, the matcher, the inference engine, and the image processing routines are controlled by the blackboard control architecture.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"15 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":"127382345","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 authors present the formulation of an improved neural architecture, a modified adaptive resonance theory (ART), for the enhancement of binary images in the presence of noise. The two-layer ART model developed by G.A. Carpenter and S. Grossberg (1987) is further incorporated into a four-layer network. The operation and performance of ART1 in classifying binary input patterns is first investigated. Based on ART1, a noise filtering architecture is devised whereby preestablished recognition categories are used as region or contour detection exemplars in order to fill in the gaps and smooth the contours of a noisy binary image without any prior knowledge of the image itself.<>
{"title":"A neural architecture applied to the enhancement of noisy binary images without prior knowledge","authors":"F. Shih, J. Moh, Henry Bourne","doi":"10.1109/TAI.1990.130423","DOIUrl":"https://doi.org/10.1109/TAI.1990.130423","url":null,"abstract":"The authors present the formulation of an improved neural architecture, a modified adaptive resonance theory (ART), for the enhancement of binary images in the presence of noise. The two-layer ART model developed by G.A. Carpenter and S. Grossberg (1987) is further incorporated into a four-layer network. The operation and performance of ART1 in classifying binary input patterns is first investigated. Based on ART1, a noise filtering architecture is devised whereby preestablished recognition categories are used as region or contour detection exemplars in order to fill in the gaps and smooth the contours of a noisy binary image without any prior knowledge of the image itself.<<ETX>>","PeriodicalId":366276,"journal":{"name":"[1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence","volume":"51 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":"116771229","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：