ISSN:0954-0091    

DOI:10.1080/09540099308915699

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor

摘要:

We describe a hybrid knowledge representation and reasoning system that integrates a rule-based reasoner with a type hierarchy and can accommodate multiple dynamic instantiations of predicates. The system—which is an extension of the reasoner described in Shastri and Ajjanagadde (1990)maintains and propagates variable bindings using temporally synchronous (i.e. in-phase)firing of appropriate nodes, and can perform a broad class of reasoning with extreme efficiency. The type hierarchy allows the system to encode generic facts such as ‘cats prey on bird’ and rules such as ‘if x preys on y then y is scared of ’ and use them to infer that Tweety the canary is scared of Sylvester the cat. The system can also encode qualified rules such as ‘if an animate agent collides with a solid object then the agent gets hur’. The ability to accommodate multiple dynamic instantiations of any predicate allows the system to handle a much broader class of inferences, including those involving transitivity and bounded recursion. The proposed system can answer queries in lime which is independent of the size of the knowledge base, and is only proportional to the length of the shortest derivation of the query.

ISSN:0954-0091    

DOI:10.1080/09540099308915700

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor

摘要:

Traditionally, semantic memory is considered to be composed of a single layer of knowledge. This layer can be thought of as encoding the systematic relations that underlie the regularities in our cognitive world. In this article, this notion is extended to include a second layer, so that semantic memory now consists of two tiers. The second tier asserts that each of our concepts has attached to it an associational cloud of knowledge that encodes the non-systematic knowledge associated with these concepts, or what Fillmore (1982) calls a concept's background frame knowledge. Semantic memory is constructed from co-occurrence statistics gathered from the Wall Street Journal text corpus. The associational knowledge is encoded from a set of semantic features extracted from the categories o/Roget's Thesaurus. This approach of the encoding and use of world knowledge is significant in that it supports an architecture that can scale up.

ISSN:0954-0091    

DOI:10.1080/09540099308915701

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor

摘要:

The paper discusses a connectionist implementation of knowledge engineering concepts and concepts related to production systems in particular. Production systems are one of the most used artificial intelligence techniques as well as a widely explored model of cognition. The use of neural networks for building connectionist production systems opens the door for developing production systems with partial match and approximate reasoning. An architecture of a neural production system (NPS) and its third realization—NPS3, designed to facilitate approximate reasoning—are presented in the paper. NPS3 facilitates partial match between facts and rules, variable binding, different conflict resolution strategies and chain inference. Facts are represented in a working memory by so-called certainty degrees. Different inference control parameters are attached to every production rule. Some of them are known neuronal parameters, receiving an engineering meaning here. Others, which have their context in knowledge engineering, have been implemented in a connectionist way. The partial match implemented in NPS3 is demonstrated on the same test production system as used by other authors. The ability of NPS3 for approximate reasoning is illustrated by reasoning over a set of simple diagnostic productions and a set of decision support fuzzy rules.

ISSN:0954-0091    

DOI:10.1080/09540099308915702

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor

摘要:

Recurrent neural networks readily process, learn and generate temporal sequences. In addition, they have been shown to have impressive computational power. Recurrent neural networks can be trained with symbolic string examples encoded as temporal sequences to behave like sequential finite slate recognizers. We discuss methods for extracting, inserting and refining symbolic grammatical rules for recurrent networks. This paper discusses various issues: how rules are inserted into recurrent networks, how they affect training and generalization, and how those rules can be checked and corrected. The capability of exchanging information between a symbolic representation (grammatical rules)and a connectionist representation (trained weights) has interesting implications. After partially known rules are inserted, recurrent networks can be trained to preserve inserted rules that were correct and to correct through training inserted rules that were ‘incorrec’—rules inconsistent with the training data.

ISSN:0954-0091    

DOI:10.1080/09540099308915703

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor

摘要:

This paper describes RAPTURE—a system for revising probabilistic knowledge bases that combines connectionist and symbolic learning methods. RAPTURE uses a modified version of backpropagation to refine the certainty factors of a probabilistic rule base and it uses ID3's information-gain heuristic to add new rules. Results on refining three actual expert rule bases demonstrate that this combined approach generally performs better than previous methods.

ISSN:0954-0091    

DOI:10.1080/09540099308915704

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor

摘要:

The concepts of knowledge-based systems and machine learning are combined by integrating an expert system and a constructive neural networks learning algorithm. Two approaches are explored: embedding the expert system directly and converting the expert system rule base into a neural network. This initial system is then extended by constructively learning additional hidden units in a problem-specific manner. Experiments performed indicate that generalization of a combined system surpasses that of each system individually.

ISSN:0954-0091    

DOI:10.1080/09540099308915705

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor

摘要:

This paper deals with the integration of neural and symbolic approaches. It focuses on associative memories where a connectionist architecture tries to provide a storage and retrieval component for the symbolic level. In this light, the classic model for associative memory, the Hopfield network is briefly reviewed. Then, a new model for associative memory, the hybrid Hopfield-clique network is presented in detail. Its application to a typically symbolic task, the post -processing of the output of an optical character recognizer, is also described. In the author's view, the hybrid Hopfield -clique network constitutes an example of a successful integration of the two approaches. It uses a symbolic learning scheme to train a connectionist network, and through this integration, it can provide perfect storage and recall. As a conclusion, an analysis of what can be learned from this specific architecture is attempted. In the case of this model, a guarantee for perfect storage and recall can only be given because it was possible to analyze the problem using the well-defined symbolic formalism of graph theory. In general, we think that finding an adequate formalism for a given problem is an important step towards solving it.

ISSN:0954-0091    

DOI:10.1080/09540099308915706

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor

摘要:

The growing interest in integrating symbolic and subsymbolic computing techniques is manifested by the increasing number of hybrid systems that employ both methods of processing. In this paper, a general-purpose mechanism for linking symbolic and subsymbolic computing is introduced. Through the use of programming abstractions, an intermediary agent called a supervisor is created and bound to each subsymbolic network. The role of a supervisor is to monitor and control the network behavior and interpret its output. Details of the subsymbolic computation are hidden behind a higher level interface, enabling symbolic and sybsymbolic components to interact at corresponding conceptual levels. Module level parallelism is achieved because subsymbolic modules execute independently. Methods for construction of hierarchical systems of subsymbolic modules are also provided.

ISSN:0954-0091    

DOI:10.1080/09540099308915707

出版商:Taylor & Francis Group    

年代:1993

数据来源: Taylor