<OT> New Posting: ROA-917

[roa at ruccs.rutgers.edu]

ROA 917-0607

Gradual learning and convergence

Joe Pater <pater at linguist.umass.edu>

Direct link: http://roa.rutgers.edu/view.php3?roa=917


Abstract:
This squib presents a simple abstract learning problem on
which the Gradual Learning Algorithm (GLA; Boersma 1998,
Boersma and Hayes 2001) fails. It then discusses the relationship
of the GLA to the provably convergent Perceptron learning
algorithm (Rosenblatt 1958), and shows that the learning
problem is solved by a combination of the Perceptron update
rule with Harmonic Grammar (Smolensky and Legendre 2006).

Comments: To appear in Linguistic Inquiry
Keywords: learnability theory, harmonic grammar, GLA
Areas: Phonology,Learnability
Type: Squib

Direct link: http://roa.rutgers.edu/view.php3?roa=917