Neural Network Exploration Using Optimal Experiment Design
dc.date.accessioned | 2004-10-08T20:35:52Z | |
dc.date.accessioned | 2018-11-24T10:17:15Z | |
dc.date.available | 2004-10-08T20:35:52Z | |
dc.date.available | 2018-11-24T10:17:15Z | |
dc.date.issued | 1994-06-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/6631 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/6631 | |
dc.description.abstract | 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. | en_US |
dc.format.extent | 131203 bytes | |
dc.format.extent | 492706 bytes | |
dc.language.iso | en_US | |
dc.title | Neural Network Exploration Using Optimal Experiment Design | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AIM-1491.pdf | 492.7Kb | application/pdf | View/ |
AIM-1491.ps.Z | 131.2Kb | application/octet-stream | View/ |