Training Algorithm for Extra Reduced Size Lattice-Ladder Multilayer Perceptrons
2003 (English)Report (Other academic)
A quick gradient training algorithm for a specific neural network structure called an extra reduced size lattice-ladder multilayer perceptron is introduced. Presented derivation of the algorithm utilizes recently found by author simplest way of exact computation of gradients for rotation parameters of lattice-ladder filter. Developed neural network training algorithm is optimal in terms of minimal number of constants, multiplication and addition operations, while the regularity of the structure is also preserved.
Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2003. , 14 p.
LiTH-ISY-R, ISSN 1400-3902 ; 2499
lattice–ladder filter, lattice–ladder multilayer perceptron, adaptation, gradient adaptive lattice algorithms.
IdentifiersURN: urn:nbn:se:liu:diva-55916ISRN: LiTH-ISY-R-2499OAI: oai:DiVA.org:liu-55916DiVA: diva2:316613