Neural Network Exploration Using Optimal Experiment Design

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6631

Full metadata record

DC Field	Value	Language
dc.creator	Cohn, David A.	-
dc.date	2004-10-08T20:35:52Z	-
dc.date	2004-10-08T20:35:52Z	-
dc.date	1994-06-01	-
dc.date.accessioned	2013-10-09T02:46:19Z	-
dc.date.available	2013-10-09T02:46:19Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1491	-
dc.identifier	http://hdl.handle.net/1721.1/6631	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	We consider the question "How should one act when the only goal is to learn as much as possible?" Building on the theoretical results of Fedorov [1972] and MacKay [1992], we apply techniques from Optimal Experiment Design (OED) to guide the query/action selection of a neural network learner. We demonstrate that these techniques allow the learner to minimize its generalization error by exploring its domain efficiently and completely. We conclude that, while not a panacea, OED-based query/action has much to offer, especially in domains where its high computational costs can be tolerated.	-
dc.format	131203 bytes	-
dc.format	492706 bytes	-
dc.format	application/octet-stream	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1491	-
dc.title	Neural Network Exploration Using Optimal Experiment Design	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI