Types and Quantifiers in SHRUTI: A Connectionist Model of Rapid Reasoning and Relational Processing

In order to understand language, a hearer must draw inferences to establish referential and causal coherence. Hence our ability to understand language suggests that we are capable of performing a wide range of inferences rapidly and spontaneously. This poses a challenge for cognitive science: How can a system of slow neuron-like elements encode a large body of knowledge and perform inferences with such speed? SHRUTI attempts to answer this question by demonstrating how a neurally plausible network can encode a large body of semantic and episodic facts, and systematic rule-like knowledge, and yet perform a range of inferences within a few hundred milliseconds. This paper describes a novel representation of types and instances in SHRUTI that supports the encoding of rules and facts involving types and quantifiers, enables SHRUTI to distinguish between hypothesized and asserted entities, and facilitates the dynamic instantiation and unification of entities during inference.

[1]  Jerry R. Hobbs,et al.  Interpretation as Abduction , 1993, Artif. Intell..

[2]  G. Lakoff,et al.  Women, Fire, and Dangerous Things: What Categories Reveal about the Mind , 1988 .

[3]  C. von der Malsburg,et al.  Am I Thinking Assemblies , 1986 .

[4]  Lokendra Shastri,et al.  Recruitment of binding and binding-error detector circuits via long-term potentiation , 1999, Neurocomputing.

[5]  L. Shastri,et al.  From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony , 1993, Behavioral and Brain Sciences.

[6]  Jerome A. Feldman,et al.  Extending Embodied Lexical Development , 1998 .

[7]  D. R. Mani,et al.  Reflexive Reasoning with Multiple Instantiation in a Connectionist Reasoning System with a Type Hierarchy , 1993 .

[8]  T. Bliss,et al.  A synaptic model of memory: long-term potentiation in the hippocampus , 1993, Nature.

[9]  R. Sun.  On Variable Binding in Connectionist Networks , 1992 .

[10]  L. Shastri,et al.  Knowledge Fusion in the Large - taking a cue from the brain , 1999 .

[11]  John A. Barnden,et al.  Encoding techniques for complex information structures in connectionist systems , 1991 .

[12]  Michael G. Dyer,et al.  High-level Inferencing in a Connectionist Network , 1989 .

[13]  John E. Hummel,et al.  Distributed representations of structure: A theory of analogical access and mapping. , 1997 .

[14]  J E Lisman,et al.  Storage of 7 +/- 2 short-term memories in oscillatory subcycles , 1995, Science.

[15]  Edward K. Vogel,et al.  The capacity of visual working memory for features and conjunctions , 1997, Nature.

[16]  G. Lakoff.  Women, fire, and dangerous things : what categories reveal about the mind , 1989 .

[17]  L. Shastri,et al.  A Connectionist Treatment of Negation and Inconsistency , 1996 .

[18]  W. Singer.  Synchronization of cortical activity and its putative role in information processing and learning. , 1993, Annual review of physiology.

[19]  Keith Stenning,et al.  Extension of the temporal synchrony approach to dynamic variable bindingin a connectionist inference system , 1995, Knowl. Based Syst..

[20]  Lokendra Shastri,et al.  A Connectionist Encoding of Schemas and Reactive Plans , 1997 .

[21]  T. Odlin.  Women, Fire, and Dangerous Things: What Categories Reveal about the Mind , 1988 .

[22]  Lokendra Shastri,et al.  Exploiting Temporal Binding to Learn Relational Rules within a Connectionist Network , 1997 .

[23]  Terry Regier,et al.  The Human Semantic Potential: Spatial Language and Constrained Connectionism , 1996 .