Minds and Machines 9 (3):383-398 (1999)
Minds are said to be systematic: the capacity to entertain certain thoughts confers to other related thoughts. Although an important property of human cognition, its implication for cognitive architecture has been less than clear. In part, the uncertainty is due to lack of precise accounts on the degree to which cognition is systematic. However, a recent study on learning transfer provides one clear example. This study is used here to compare transfer in humans and feedforward networks. Simulations and analysis show, that while feedforward networks with shared weights are capable of exhibiting transfer, they cannot support the same degree of transfer as humans. One interpretation of these results is that common connectionist models lack explicit internal representations permitting rapid learning.
|Keywords||classicism connectionism Klein group learning transfer normalization systematicity weight sharing|
|Categories||categorize this paper)|
References found in this work BETA
No references found.
Citations of this work BETA
Abstract Analogies Not Primed by Relations Learned as Object Transformations.Steven Phillips - 2008 - Behavioral and Brain Sciences 31 (4):393-394.
Similar books and articles
Learning to Learn Causal Models.Charles Kemp, Noah D. Goodman & Joshua B. Tenenbaum - 2010 - Cognitive Science 34 (7):1185-1243.
Connectionism, Explicit Rules, and Symbolic Manipulation.Robert F. Hadley - 1993 - Minds and Machines 3 (2):183-200.
Prospects for Automatic Recoding of Inputs in Connectionist Learning.Nicolas Szilas & Thomas R. Shultz - 1997 - Behavioral and Brain Sciences 20 (1):81-82.
The Governance of University Knowledge Transfer: A Critical Review of the Literature.Aldo Geuna & Alessandro Muscio - 2009 - Minerva 47 (1):93-114.
Category Transfer in Sequential Causal Learning: The Unbroken Mechanism Hypothesis.York Hagmayer, Björn Meder, Momme von Sydow & Michael R. Waldmann - 2011 - Cognitive Science 35 (5):842-873.
Neo-Associativism: Limited Learning Transfer Without Binding Symbol Representations.Steven Phillips - 2002 - Behavioral and Brain Sciences 25 (3):350-351.
Systematicity: Psychological Evidence with Connectionist Implications.S. Phillips & G. S. Halford - unknown
Are Feedforward and Recurrent Networks Systematic? Analysis and Implications for a Connectionist Cognitive Architecture.S. Phillips - 1998 - Philosophical Explorations.
Added to index2009-01-28
Total downloads51 ( #103,717 of 2,178,176 )
Recent downloads (6 months)1 ( #316,504 of 2,178,176 )
How can I increase my downloads?