Semantic systematicity and context in connectionist networks

Boden, Mikael and Niklasson, Lars (2000) Semantic systematicity and context in connectionist networks. Connection Science, 12 2: 111-142. doi:10.1080/09540090050129754

Author Boden, Mikael
Niklasson, Lars
Title Semantic systematicity and context in connectionist networks
Journal name Connection Science   Check publisher's open access policy
ISSN 0954-0091
Publication date 2000-06
Sub-type Article (original research)
DOI 10.1080/09540090050129754
Volume 12
Issue 2
Start page 111
End page 142
Total pages 32
Place of publication Hampshire, UK
Publisher Taylor & Francis
Collection year 2000
Language eng
Subject C1
380304 Neurocognitive Patterns and Neural Networks
780108 Behavioural and cognitive sciences
Abstract Fodor and Pylyshyn argued that connectionist models could not be used to exhibit and explain a phenomenon that they termed systematicity, and which they explained by possession of composition syntax and semantics for mental representations and structure sensitivity of mental processes. This inability of connectionist models, they argued, was particularly serious since it meant that these models could not be used as alternative models to classical symbolic models to explain cognition. In this paper, a connectionist model is used to identify some properties which collectively show that connectionist networks supply means for accomplishing a stronger version of systematicity than Fodor and Pylyshyn opted for. It is argued that 'context-dependent systematicity' is achievable within a connectionist framework. The arguments put forward rest on a particular formulation of content and context of connectionist representation, firmly and technically based on connectionist primitives in a learning environment. The perspective is motivated by the fundamental differences between the connectionist and classical architectures, in terms of prerequisites, lower-level functionality and inherent constraints. The claim is supported by a set of experiments using a connectionist architecture that demonstrates both an ability of enforcing, what Fodor and Pylyshyn term systematic and nonsystematic processing using a single mechanism, and how novel items can be handled without prior classification. The claim relies on extended learning feedback which enforces representational context dependence.
Keyword Computer Science, Artificial Intelligence
Computer Science, Theory & Methods
Learning internal representation
Weight representations
Cognitive architecture
References Online July 2010
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collection: School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 8 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 10 Jun 2008, 13:23:38 EST