University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Stack- and Queue-like Dynamics in Recurrent Neural Networks

Grüning, A (2006) Stack- and Queue-like Dynamics in Recurrent Neural Networks Connection Science, 18. 23 - 42. ISSN 0954-0091

[img]
Preview
PDF
gruening_05_connection_science.pdf - Accepted Version
Available under License : See the attached licence file.

Download (657kB)
[img] Plain Text (licence)
licence.txt

Download (1kB)

Abstract

What dynamics do simple recurrent networks (SRNs) develop to represent stack-like and queue-like memories? SRNs have been widely used as models in cognitive science. However, they are interesting in their own right as non-symbolic computing devices from the viewpoints of analogue computing and dynamical systems theory. In this paper, SRNs are trained oil two prototypical formal languages with recursive structures that need stack-like or queue-like memories for processing, respectively. The evolved dynamics are analysed, then interpreted in terms of simple dynamical systems, and the different ease with which SRNs aquire them is related to the properties of these simple dynamical Within the dynamical systems framework, it is concluded that the stack-like language is simpler than the queue-like language, without making use of arguments from symbolic computation theory.

Item Type: Article
Additional Information: This is an electronic version of an article published in Connection Science, 18(1), 23-42(2006). Connection Science is available online at: http://www.tandfonline.com/doi/abs/10.1080/09540090500317291.
Uncontrolled Keywords: simple current networks, network dynamics, formal languages, dynamical complexity, CONTEXT-FREE, ARCHITECTURAL BIAS, LANGUAGE, TIME, COMPUTATION, RECOGNIZERS, EXTRACTION, INDUCTION, MACHINES, TAXONOMY
Related URLs:
Divisions: Faculty of Engineering and Physical Sciences > Computing Science
Depositing User: Symplectic Elements
Date Deposited: 07 Dec 2011 14:33
Last Modified: 23 Sep 2013 18:53
URI: http://epubs.surrey.ac.uk/id/eprint/22858

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800