Nonlinear adaptive prediction of speech with a pipelined recurrent neural network

New learning algorithms for an adaptive nonlinear forward predictor that is based on a pipelined recurrent neural network (PRNN) are presented. A computationally efficient gradient descent (GD) learning algorithm, together with a novel extended recursive least squares (ERLS) learning algorithm, are...

Full description

Bibliographic Details

Main Authors:	Jens Baltersee, Jonathon Chambers
Format:	Default Article
Published:	1998
Subjects:	Mechanical engineering not elsewhere classified Adaptive algorithms Neural networks Nonlinear prediction Mechanical Engineering not elsewhere classified
Online Access:	https://hdl.handle.net/2134/5817
Tags:	Add Tag No Tags, Be the first to tag this record!