Formalizing Triggers: A Learning Model for Finite Spaces

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6618

Full metadata record

DC Field	Value	Language
dc.creator	Niyogi, Partha	-
dc.creator	Berwick, Robert C.	-
dc.date	2004-10-08T20:34:33Z	-
dc.date	2004-10-08T20:34:33Z	-
dc.date	1993-11-01	-
dc.date.accessioned	2013-10-09T02:46:10Z	-
dc.date.available	2013-10-09T02:46:10Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1449	-
dc.identifier	http://hdl.handle.net/1721.1/6618	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	In a recent seminal paper, Gibson and Wexler (1993) take important steps to formalizing the notion of language learning in a (finite) space whose grammars are characterized by a finite number of parameters. They introduce the Triggering Learning Algorithm (TLA) and show that even in finite space convergence may be a problem due to local maxima. In this paper we explicitly formalize learning in finite parameter space as a Markov structure whose states are parameter settings. We show that this captures the dynamics of TLA completely and allows us to explicitly compute the rates of convergence for TLA and other variants of TLA e.g. random walk. Also included in the paper are a corrected version of GW's central convergence proof, a list of "problem states" in addition to local maxima, and batch and PAC-style learning bounds for the model.	-
dc.format	133564 bytes	-
dc.format	665289 bytes	-
dc.format	application/octet-stream	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1449	-
dc.title	Formalizing Triggers: A Learning Model for Finite Spaces	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI