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

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