Cognitive Science 40 (4):782-821 (2016)

Chris Eliasmith
University of Waterloo
Several approaches to implementing symbol-like representations in neurally plausible models have been proposed. These approaches include binding through synchrony, “mesh” binding, and conjunctive binding. Recent theoretical work has suggested that most of these methods will not scale well, that is, that they cannot encode structured representations using any of the tens of thousands of terms in the adult lexicon without making implausible resource assumptions. Here, we empirically demonstrate that the biologically plausible structured representations employed in the Semantic Pointer Architecture approach to modeling cognition do scale appropriately. Specifically, we construct a spiking neural network of about 2.5 million neurons that employs semantic pointers to successfully encode and decode the main lexical relations in WordNet, which has over 100,000 terms. In addition, we show that the same representations can be employed to construct recursively structured sentences consisting of arbitrary WordNet concepts, while preserving the original lexical structure. We argue that these results suggest that semantic pointers are uniquely well-suited to providing a biologically plausible account of the structured representations that underwrite human cognition.
Keywords Knowledge representation  Scaling  Vector symbolic architecture  Neural network  Biologically plausible  Connectionism  WordNet
Categories No categories specified
(categorize this paper)
DOI 10.1111/cogs.12261
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

PhilArchive copy

Upload a copy of this paper     Check publisher's policy     Papers currently archived: 69,066
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

Recursive Distributed Representations.Jordan B. Pollack - 1990 - Artificial Intelligence 46 (1-2):77-105.

View all 13 references / Add more references

Citations of this work BETA

Add more citations

Similar books and articles

How is Representation Learned?James R. Williamson - 1998 - Behavioral and Brain Sciences 21 (4):484-484.
Will the Neural Blackboard Architecture Scale Up to Semantics?Michael G. Dyer - 2006 - Behavioral and Brain Sciences 29 (1):77-78.
Representation, Evolution and Embodiment.Michael L. Anderson - 2005 - Theoria Et Historia Scientarum.


Added to PP index

Total views
27 ( #420,546 of 2,498,777 )

Recent downloads (6 months)
2 ( #280,195 of 2,498,777 )

How can I increase my downloads?


My notes