From simple associations to systematic reasoning: A connectionist representation of rules, variables, and dynamic binding using temporal synchrony
David Bourget (Western Ontario)
David Chalmers (ANU, NYU)
Rafael De Clercq
Jack Alan Reynolds
Learn more about PhilPapers
Behavioral and Brain Sciences 16 (3):417-51 (1993)
Human agents draw a variety of inferences effortlessly, spontaneously, and with remarkable efficiency – as though these inferences were a reflexive response of their cognitive apparatus. Furthermore, these inferences are drawn with reference to a large body of background knowledge. This remarkable human ability seems paradoxical given the complexity of reasoning reported by researchers in artificial intelligence. It also poses a challenge for cognitive science and computational neuroscience: How can a system of simple and slow neuronlike elements represent a large body of systemic knowledge and perform a range of inferences with such speed? We describe a computational model that takes a step toward addressing the cognitive science challenge and resolving the artificial intelligence paradox. We show how a connectionist network can encode millions of facts and rules involving n-ary predicates and variables and perform a class of inferences in a few hundred milliseconds. Efficient reasoning requires the rapid representation and propagation of dynamic bindings. Our model (which we refer to as SHRUTI) achieves this by representing (1) dynamic bindings as the synchronous firing of appropriate nodes, (2) rules as interconnection patterns that direct the propagation of rhythmic activity, and (3) long-term facts as temporal pattern-matching subnetworks. The model is consistent with recent neurophysiological evidence that synchronous activity occurs in the brain and may play a representational role in neural information processing. The model also makes specific psychologically significant predictions about the nature of reflexive reasoning. It identifies constraints on the form of rules that may participate in such reasoning and relates the capacity of the working memory underlying reflexive reasoning to biological parameters such as the lowest frequency at which nodes can sustain synchronous oscillations and the coarseness of synchronization
|Keywords||binding problem connectionism knowledge representation long-term memory neural oscillations reasoning short-term memory systematicity temporal synchrony working memory|
|Categories||categorize this paper)|
|Through your library||Configure|
Similar books and articles
Michael G. Dyer (2006). Will the Neural Blackboard Architecture Scale Up to Semantics? Behavioral and Brain Sciences 29 (1):77-78.
John A. Barnden & Kankanahalli Srinivas (1996). Quantification Without Variables in Connectionism. Minds and Machines 6 (2):173-201.
Alice G. B. ter Meulen (2003). Cognitive Modelling of Human Temporal Reasoning. Behavioral and Brain Sciences 26 (5):623-624.
Satoshi Tojo & Katsumi Nitta (1997). Similarity of Legal Cases: From Temporal Relations of Affairs. [REVIEW] Artificial Intelligence and Law 5 (1-2):161-176.
Antonino Raffone & Cees van Leeuwen (2001). Chaos and Neural Coding: Is the Binding Problem a Pseudo-Problem? Behavioral and Brain Sciences 24 (5):826-827.
Marcello Guarini (2001). A Defence of Connectionism Against the "Syntactic" Argument. Synthese 128 (3):287-317.
Leonidas A. A. Doumas, Keith J. Holyoak & John E. Hummel (2006). The Problem with Using Associations to Carry Binding Information. Behavioral and Brain Sciences 29 (1):74-75.
Lokendra Shastri (2006). Comparing the Neural Blackboard and the Temporal Synchrony-Based SHRUTI Architectures. Behavioral and Brain Sciences 29 (1):84-86.
Added to index2009-01-28
Total downloads26 ( #55,364 of 1,004,774 )
Recent downloads (6 months)1 ( #64,743 of 1,004,774 )
How can I increase my downloads?