A Connectionist Approach to Knowledge Representation and Limited Inference

Although the connectionist approach has lead to elegant solutions to a number of problems in cognitive science and artificial intelligence, its suitability for dealing with problems in knowledge representation and inference has often been questioned. This paper partly answers this criticism by demonstrating that effective solutions to certain problems in knowledge representation and limited inference can be found by adopting a connectionist approach. The paper presents a connectionist realization of semantic networks, that is, it describes how knowledge about concepts, their properties, and the hierarchical relationship between them may be encoded as an Interpreter-free massively parallel network of simple processing elements that can solve an interesting class of inherltonce and recognlt/on problems extremely fast-in time proportional to the depth of the conceptual hierarchy. The connectionist realization is based on an evidential formulation that leads to principled solutions to the problems of exceptions and conflicting m&p/e lnherftance situations during inheritance, and the best-match or partlolmatch computation during recognition. The paper also identifies constraints that must be satisfied by the conceptual structure in order to arrive at an efficient parallel realization.

[1]  Allan Collins,et al.  A spreading-activation theory of semantic processing , 1975 .

[2]  Dana H. Ballard,et al.  Parallel Logical Inference and Energy Minimization , 1986, AAAI.

[3]  Scott E. Fahlman,et al.  NETL: A System for Representing and Using Real-World Knowledge , 1979, CL.

[4]  E. Rosch.  Cognitive Representations of Semantic Categories. , 1975 .

[5]  Teuvo Kohonen,et al.  Storage and Processing of Information in Distributed Associative Memory Systems , 1981 .

[6]  James F. Allen,et al.  Knowledge Retrieval as Limited Inference , 1982, CADE.

[7]  Raymond Reiter,et al.  A Logic for Default Reasoning , 1987, Artif. Intell..

[8]  Ronald J. Brachman,et al.  An Overview of the KL-ONE Knowledge Representation System , 1985, Cogn. Sci..

[9]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[10]  Lenhart K. Schubert,et al.  Determining Type, Part, Color, and Time Relationships , 1983, Computer.

[11]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[12]  A. Tversky,et al.  Extensional versus intuitive reasoning: the conjunction fallacy in probability judgment , 1983 .

[13]  J. Austin.  Associative memory , 1987 .

[14]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[15]  W A Wickelgren,et al.  Chunking and consolidation: a theoretical synthesis of semantic networks, configuring in conditioning, S--R versus congenitive learning, normal forgetting, the amnesic syndrome, and the hippocampal arousal system. , 1979, Psychological review.

[16]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[17]  Lokendra Shastri,et al.  Semantic Networks: An Evidential Formalization and Its Connectionist Realization , 1988 .

[18]  Henry E. Kyburg,,et al.  The Reference Class , 1983, Philosophy of Science.

[19]  Eugene Charniak,et al.  A Common Representation for Problem-Solving and Language-Comprehension Information , 1981, Artif. Intell..

[20]  Eugene Charniak,et al.  Passing Markers: A Theory of Contextual Influence in Language Comprehension , 1983, Cogn. Sci..

[21]  E. T. Jaynes,et al.  Where do we Stand on Maximum Entropy , 1979 .

[22]  Eugene Charniak,et al.  The Bayesian Basis of Common Sense Medical Diagnosis , 1983, AAAI.

[23]  Lokendra Shastri.  A Connectionist Approach to Knowledge Representation and Limited Inference , 1988 .

[24]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[25]  Daniel G. Bobrow,et al.  On Overview of KRL, a Knowledge Representation Language , 1976, Cogn. Sci..

[26]  Raymond Reiter,et al.  On Inheritance Hierarchies With Exceptions , 1983, AAAI.