creators_name: Gayler, Ross W.
creators_id: r.gayler
type: confpaper
datestamp: 2004-12-11
lastmod: 2011-03-11 08:55:45
metadata_visibility: show
title: Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience
ispublished: unpub
subjects: comp-sci-lang
subjects: comp-neuro-sci
subjects: comp-sci-art-intel
full_text_status: public
keywords: connectionist
compositionality
binding
note: This is a slightly updated version of the refereed paper presented at the conference.
abstract: Jackendoff (2002) posed four challenges that linguistic combinatoriality and rules of language present to theories of brain function. The essence of these problems is the question of how to neurally instantiate the rapid construction and transformation of the compositional structures that are typically taken to be the domain of symbolic processing.  He contended that typical connectionist approaches fail to meet these challenges and that the dialogue between linguistic theory and cognitive neuroscience will be relatively unproductive until the importance of these problems is widely recognised and the challenges answered by some technical innovation in connectionist modelling.  This paper claims that a little-known family of connectionist models (Vector Symbolic Architectures) are able to meet Jackendoff's challenges.
date: 2003
date_type: published
refereed: FALSE
referencetext: Anderson, J. A., Silverstein, J. W., Ritz, S. A., & Jones, R. S. (1977). Distinctive features, categorical perception, and probability learning: Some applications of a neural model. Psychological Review, 84, 413-451.

Arathorn, D. W. (2002). Map-seeking circuits in visual cognition: A computational mechanism for biological and machine vision. Stanford, CA, USA: Stanford University Press.

Bod, R. & Scha, R. (1997). Data-oriented language processing: An overview. In S. Young & G. Bloothooft (Eds.) Corpus-based methods in language and speech processing. Boston, MA, USA: Kluwer Academic Publishers. (http://turing.wins.uva.nl/~rens/overview.ps)

Copestake, A. (2002). Implementing typed feature structure grammars. Stanford, CA, USA: CSLI Publications.

Feldman, J. (2002, August). Neural binding. Connectionists Mailing List [On-line discussion group], 5th August, 2002. (http://www-2.cs.cmu.edu/afs/cs.cmu.edu/project/connect/connect-archives/arch.2002-08.gz see 0005.txt and also 8, 9, 18, & 21)

Gayler, R. W. (1998).  Multiplicative binding, representation operators, and analogy [Abstract of poster].  In K. Holyoak, D. Gentner & B. Kokinov (Eds.), Advances in analogy research: Integration of theory and data from the cognitive, computational, and neural sciences. Sofia, Bulgaria: New Bulgarian University. (http://cogprints.ecs.soton.ac.uk/archive/00000502/ for full poster)

Gayler, R. W., & Wales, R. (1998).  Connections, binding, unification, and analogical promiscuity.  In K. Holyoak, D. Gentner & B. Kokinov (Eds.), Advances in analogy research: Integration of theory and data  from the cognitive, computational, and neural sciences. Sofia, Bulgaria: New Bulgarian University. (http://cogprints.ecs.soton.ac.uk/archive/00000500/ see also 501)

Gayler, R. W., & Wales, R. (2000, February). Multiplicative binding, representation operators and analogical inference. Paper presented at the 5th Australasian Cognitive Science Conference, Melbourne, Australia.

Jackendoff, R. (2002).  Foundations of language: Brain, meaning, grammar, evolution. Oxford, UK: Oxford University Press.

Kanerva, P. (1997).  Fully distributed representation.  In Proceedings of 1997 Real World Computing Symposium (RWC'97, Tokyo). Tsukuba-city, Japan: Real World Computing Partnership. (http://www.rni.org/kanerva/rwc97.ps.gz)

Marcus, G. (2001). The algebraic mind. Cambridge, MA, USA: MIT Press.

Plate, T. A. (1994). Distributed representations and nested compositional structure. Doctoral dissertation. Department of Computer Science, University of Toronto, Toronto, Canada. (http://pws.prserv.net/tap/papers/plate.thesis.ps.gz)

Plate, T. A. (1997). A common framework for distributed representation schemes for compositional structure. In F. Maire, R. Hayward & J. Diederich (Eds.) Connectionist systems for knowledge representation and deduction. Brisbane, Australia: Queensland University of Technology Press. (http://pws.prserv.net/tap/papers/drep-framework.ps.gz)

Rachkovskij, D. A., & Kussul, E. M. (2001). Binding and normalization of binary sparse distributed representations by Context-Dependent Thinning. Neural Computation, 13(2), 411-452. (http://cogprints.ecs.soton.ac.uk/archive/00001240/)

Smolensky, P. (1990). Tensor product variable binding and the representation of symbolic structures in connectionist systems. Artificial Intelligence, 46, 159-216.
citation:   Gayler, Dr Ross W.  (2003) Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience.  [Conference Paper]    (Unpublished)  
document_url: http://cogprints.org/3983/1/Jackendoff_challenges_V3.pdf