Please use this identifier to cite or link to this item:
http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6618| Title: | Formalizing Triggers: A Learning Model for Finite Spaces |
| Issue Date: | 9-Oct-2013 |
| 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. |
| URI: | http://koha.mediu.edu.my:8181/xmlui/handle/1721 |
| Other Identifiers: | AIM-1449 http://hdl.handle.net/1721.1/6618 |
| Appears in Collections: | MIT Items |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.