liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Speeding up the Training of Lattice-Ladder Multilayer Perceptrons
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
2002 (English)Report (Other academic)
Abstract [en]

A lattice-ladder multilayer perceptron (LLMLP) is an appealing structure for advanced signal processing in a sense that it is nonlinear, possesses infinite impulse response and stability monitoring of it during training is simple. However, even moderate implementation of LLMLP training hinders the fact that a lot of storage and computation power must be allocated. In this paper we deal with the problem of computational efficiency of LLMLP training algorithms that are based on computation of gradients, e.g., backpropagation, conjugate-gradient or Levenberg-Marquardt.The paper aims to explore most computationally demanding calculations---computation of gradients for lattice (rotation)parameters. Here we find and propose to use for training of several LLMLP architectures a simplest in terms of storage and number of delay elements computation of exact gradients, assuming that the coefficients of the lattice-ladder filter are held stationary.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2002. , 30 p.
LiTH-ISY-R, ISSN 1400-3902 ; 2417
Keyword [en]
Gradient adaptive lattice algorithms, lattice–ladder filter, lattice ladder multilayer perceptron, training, estimation, adaptation, backpropagation
National Category
Control Engineering
URN: urn:nbn:se:liu:diva-55909ISRN: LiTH-ISY-R-2417OAI: diva2:316622
Available from: 2010-04-30 Created: 2010-04-30 Last updated: 2014-10-03Bibliographically approved

Open Access in DiVA

fulltext(278 kB)46 downloads
File information
File name FULLTEXT01.pdfFile size 278 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
Automatic ControlThe Institute of Technology
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 46 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 23 hits
ReferencesLink to record
Permanent link

Direct link