Stack-like and queue-like dynamics in recurrent neural networks
UNSPECIFIED. (2006) Stack-like and queue-like dynamics in recurrent neural networks. Connection Science, Volume 18 (Number 1). pp. 23-42. ISSN 0954-0091Full text not available from this repository.
Official URL: http://dx.doi.org/10.1080/09540090500317291
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:||Journal Article|
|Subjects:||Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software|
|Journal or Publication Title:||Connection Science|
|Publisher:||TAYLOR & FRANCIS LTD|
|Official Date:||March 2006|
|Number of Pages:||20|
|Page Range:||pp. 23-42|
Actions (login required)