Cognitive Science 37 (7):1193-1227 (2013)

Abstract
Human participants and recurrent (“connectionist”) neural networks were both trained on a categorization system abstractly similar to natural language systems involving irregular (“strong”) classes and a default class. Both the humans and the networks exhibited staged learning and a generalization pattern reminiscent of the Elsewhere Condition (Kiparsky, 1973). Previous connectionist accounts of related phenomena have often been vague about the nature of the networks’ encoding systems. We analyzed our network using dynamical systems theory, revealing topological and geometric properties that can be directly compared with the mechanisms of non-connectionist, rule-based accounts. The results reveal that the networks “contain” structures related to mechanisms posited by rule-based models, partly vindicating the insights of these models. On the other hand, they support the one mechanism (OM), as opposed to the more than one mechanism (MOM), view of symbolic abstraction by showing how the appearance of MOM behavior can arise emergently from one underlying set of principles. The key new contribution of this study is to show that dynamical systems theory can allow us to explicitly characterize the relationship between the two perspectives in implemented models
Keywords Dynamical systems theory  Emergence  Recurrent neural networks  Default Categorization  Abstraction  Rule learning  Elsewhere Condition  Connectionist (neural network) modeling
Categories (categorize this paper)
DOI 10.1111/cogs.12072
Options
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: 72,607
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

Finding Structure in Time.Jeffrey L. Elman - 1990 - Cognitive Science 14 (2):179-211.
A Logic for Default Reasoning.Ray Reiter - 1980 - Artificial Intelligence 13 (1-2):81-137.

View all 30 references / Add more references

Citations of this work BETA

No citations found.

Add more citations

Similar books and articles

A Step in the Right Direction.Mary Ann Metzger - 1993 - Journal Od Mathematical Psychology 37 (3):477-485.
Some Neural Networks Compute, Others Don't.Gualtiero Piccinini - 2008 - Neural Networks 21 (2-3):311-321.

Analytics

Added to PP index
2013-08-10

Total views
52 ( #221,807 of 2,533,629 )

Recent downloads (6 months)
1 ( #389,998 of 2,533,629 )

How can I increase my downloads?

Downloads

My notes