Quick Training Algorithm for Extra Reduced Size Lattice‐Ladder Multilayer Perceptrons

Article type: Research Article

Authors: Navakauskas, Dalius

Affiliations: Department of Radioelectronics, Vilnius Gediminas Technical University, Naugarduko 41, LT‐2600 Vilnius, Lithuania, e‐mail: dalius@el.vtu.lt

Note: [] For the financial support author would like to thank prof. L. Ljung (Linköping University, Sweden), The Royal Swedish Academy of Sciences and The Swedish Institute – New Visby project Ref. No. 2473/2002 (381/T81).

Abstract: 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.

Keywords: lattice‐ladder filter, lattice‐ladder multilayer perceptron, adaptation, gradient adaptive lattice algorithms

Journal: Informatica, vol. 14, no. 2, pp. 223-236, 2003