Using Recurrent Networks for Dimensionality Reduction

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7045

Full metadata record

DC Field	Value	Language
dc.creator	Jones, Michael J.	-
dc.date	2004-10-20T20:23:37Z	-
dc.date	2004-10-20T20:23:37Z	-
dc.date	1992-09-01	-
dc.date.accessioned	2013-10-09T02:48:05Z	-
dc.date.available	2013-10-09T02:48:05Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AITR-1396	-
dc.identifier	http://hdl.handle.net/1721.1/7045	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	This report explores how recurrent neural networks can be exploited for learning high-dimensional mappings. Since recurrent networks are as powerful as Turing machines, an interesting question is how recurrent networks can be used to simplify the problem of learning from examples. The main problem with learning high-dimensional functions is the curse of dimensionality which roughly states that the number of examples needed to learn a function increases exponentially with input dimension. This thesis proposes a way of avoiding this problem by using a recurrent network to decompose a high-dimensional function into many lower dimensional functions connected in a feedback loop.	-
dc.format	2167097 bytes	-
dc.format	1325986 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AITR-1396	-
dc.title	Using Recurrent Networks for Dimensionality Reduction	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI