From an a priori RNN to an a posteriori PRNN nonlinear predictor

We provide an analysis of nonlinear time series prediction schemes, from a common recurrent neural network (RNN) to the pipelined recurrent neural network (PRNN), which consists of a number of nested small-scale RNNs. All these schemes are shown to be suitable for nonlinear autoregressive moving ave...

Full description

Bibliographic Details

Main Authors:	Danilo P. Mandic, Jonathon Chambers
Format:	Default Conference proceeding
Published:	1998
Subjects:	Mechanical engineering not elsewhere classified untagged Mechanical Engineering not elsewhere classified
Online Access:	https://hdl.handle.net/2134/5816
Tags:	Add Tag No Tags, Be the first to tag this record!