Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 7-Day Trial for You or Your Team.

Learn More →

On the Subsymbolic Nature of a PDP Architecture that Uses a Nonmonotonic Activation Function

On the Subsymbolic Nature of a PDP Architecture that Uses a Nonmonotonic Activation Function PDP networks that use nonmonotonic activation functions often produce hidden unit regularities that permit the internal structure of these networks to be interpreted (Berkeley et al., 1995; McCaughan, 1997; Dawson, 1998). In particular, when the responses of hidden units to a set of patterns are graphed using jittered density plots, these plots organize themselves into a set of discrete stripes or bands. In some cases, each band is associated with a local interpretation. On the basis of these observations, Berkeley (2000) has suggested that these bands are both subsymbolic and symbolic in nature, and has used the analysis of one network to support the claim that there are fewer differences between symbols and subsymbols than one might expect. We suggest below that this conclusion is premature. First, in many cases the local interpretation of each band is difficult to relate to the interpretation of a network's response; a more appropriate relationship only emerges when a band associated with one hidden unit is considered in the context of other bands associated with other hidden units (i.e., interpretations of distributed representations are more useful than interpretations of local representations). Second, the content that a band designates to an external observer (i.e., the interpretation assigned to a band by the researcher) can be quite different from the content that a band designates to the output units of the network itself.. We use two different network simulations – including the one described by Berkeley (2000) – to illustrate these points. We conclude that current evidence involving interpretations of nonmonotonic PDP networks actually illustrates the differences between symbolic and subsymbolic processing. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Minds and Machines Springer Journals

On the Subsymbolic Nature of a PDP Architecture that Uses a Nonmonotonic Activation Function

Dawson, Michael; Piercey, C.
Minds and Machines , Volume 11 (2) – Oct 6, 2004
Download PDF
22 pages

Loading next page...
 
/lp/springer-journals/on-the-subsymbolic-nature-of-a-pdp-architecture-that-uses-a-0ZM1k7oRGV

References (28)

Publisher
Springer Journals
Copyright
Copyright © 2001 by Kluwer Academic Publishers
Subject
Computer Science; Artificial Intelligence (incl. Robotics); Philosophy of Mind; Game Theory, Economics, Social and Behav. Sciences; Cognitive Psychology; Philosophy of Science; Theory of Computation
ISSN
0924-6495
eISSN
1572-8641
DOI
10.1023/A:1011237306312
Publisher site
See Article on Publisher Site

Abstract

PDP networks that use nonmonotonic activation functions often produce hidden unit regularities that permit the internal structure of these networks to be interpreted (Berkeley et al., 1995; McCaughan, 1997; Dawson, 1998). In particular, when the responses of hidden units to a set of patterns are graphed using jittered density plots, these plots organize themselves into a set of discrete stripes or bands. In some cases, each band is associated with a local interpretation. On the basis of these observations, Berkeley (2000) has suggested that these bands are both subsymbolic and symbolic in nature, and has used the analysis of one network to support the claim that there are fewer differences between symbols and subsymbols than one might expect. We suggest below that this conclusion is premature. First, in many cases the local interpretation of each band is difficult to relate to the interpretation of a network's response; a more appropriate relationship only emerges when a band associated with one hidden unit is considered in the context of other bands associated with other hidden units (i.e., interpretations of distributed representations are more useful than interpretations of local representations). Second, the content that a band designates to an external observer (i.e., the interpretation assigned to a band by the researcher) can be quite different from the content that a band designates to the output units of the network itself.. We use two different network simulations – including the one described by Berkeley (2000) – to illustrate these points. We conclude that current evidence involving interpretations of nonmonotonic PDP networks actually illustrates the differences between symbolic and subsymbolic processing.

Journal

Minds and Machines – Springer Journals

Published: Oct 6, 2004

There are no references for this article.