Fletcher, P (2001) Connectionist learning of regular graph grammars. Connection Science, 13 (2). 127 - 188.

[img]
Preview
Text
Connectionist learning of regular graph grammars (PFletcher).pdf

Download (715kB) | Preview

Abstract

This paper presents a new connectionist approach to grammatical inference. Using only positive examples, the algorithm learns regular graph grammars, representing two-dimensional iterative structures drawn on a discrete Cartesian grid. This work is intended as a case study in connectionist symbol processing andgeometric concept formation. A grammar is represented by a self-configuring connectionist network that is analogous to a transition diagram except that it can deal with graph grammars as easily as string grammars. Learning starts with a trivial grammar, expressing nogrammatical knowledge, which is then refined, by a process of successive node splitting and merging, into a grammar adequate to describe the population of input patterns. In conclusion, I argue that the connectionist style of computation is, in some ways, better suited than sequential computation to the task of representing and manipulating recursive structures.

Item Type: Article
Uncontrolled Keywords: grammatical inference; graph grammars; neural networks; parallel parsing; regular grammars; stochastic grammars; symbol processing; unsupervised learning
Subjects: Q Science > QA Mathematics
Divisions: Faculty of Natural Sciences > School of Computing and Mathematics
Related URLs:
Depositing User: Symplectic
Date Deposited: 19 Nov 2014 12:11
Last Modified: 29 Jul 2019 13:27
URI: https://eprints.keele.ac.uk/id/eprint/64

Actions (login required)

View Item View Item