Forecasting Global Temperature Variations by Neural Networks

dc.creator	Miyano, Takaya
dc.creator	Girosi, Federico
dc.date	2004-10-20T20:49:51Z
dc.date	2004-10-20T20:49:51Z
dc.date	1994-08-01
dc.date.accessioned	2013-10-09T02:48:33Z
dc.date.available	2013-10-09T02:48:33Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1447
dc.identifier	CBCL-101
dc.identifier	http://hdl.handle.net/1721.1/7208
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	Global temperature variations between 1861 and 1984 are forecast usingsregularization networks, multilayer perceptrons and linearsautoregression. The regularization network, optimized by stochasticsgradient descent associated with colored noise, gives the bestsforecasts. For all the models, prediction errors noticeably increasesafter 1965. These results are consistent with the hypothesis that thesclimate dynamics is characterized by low-dimensional chaos and thatsthe it may have changed at some point after 1965, which is alsosconsistent with the recent idea of climate change.s
dc.format	11 p.
dc.format	342101 bytes
dc.format	403018 bytes
dc.format	application/octet-stream
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1447
dc.relation	CBCL-101
dc.subject	time series prediction
dc.subject	chaotic systems
dc.subject	neural nets
dc.subject	RBF
dc.title	Forecasting Global Temperature Variations by Neural Networks

Files in this item

Files	Size	Format	View
There are no files associated with this item.