# Show Reference: "Getting symbols out of a neural architecture"

Getting symbols out of a neural architecture Connection Science, Vol. 23, No. 2. (June 2011), pp. 109-118, doi:10.1080/09540091.2011.569880 by John E. Hummel
@article{hummel-2011,
abstract = {Traditional connectionist networks are sharply limited as general accounts of human perception and cognition because they are unable to represent relational ideas such as loves (John, Mary) or bigger-than (Volkswagen, breadbox) in a way that allows them to be manipulated as explicitly relational structures. This paper reviews and critiques the four major responses to this problem in the modelling community: (1) reject connectionism (in any form) in favour of traditional symbolic approaches to modelling the mind; (2) reject the idea that mental representations are symbolic (i.e. reject the idea that we can represent relations); and (3) attempt to represent symbolic structures in a connectionist/neural architecture by finding a way to represent role-filler bindings. Approach (3) is further subdivided into (3a) approaches based on varieties of conjunctive coding and (3b) approaches based on dynamic role-filler binding. I will argue that (3b) is necessary to get symbolic processing out of a neural computing architecture. Specifically, I will argue that vector addition is both the best way to accomplish dynamic binding and an essential part of the proper treatment of symbols in a neural architecture.},
author = {Hummel, John E.},
doi = {10.1080/09540091.2011.569880},
issn = {0954-0091},
journal = {Connection Science},
keywords = {binding, cognitive-model, computational, symbolic},
month = jun,
number = {2},
pages = {109--118},
posted-at = {2012-09-20 13:23:38},
priority = {2},
publisher = {Taylor \& Francis, Inc.},
title = {Getting symbols out of a neural architecture},
url = {http://dx.doi.org/10.1080/09540091.2011.569880},
volume = {23},
year = {2011}
}