Title :
A reduced size lattice-ladder neural network
Author :
Navakauskas, Dalius
Author_Institution :
Dept. of Radioelectron., Vilnius Gediminas Tech. Univ.
fDate :
31 Aug-2 Sep 1998
Abstract :
An idea to incorporate filters in the common structure of an artificial neural network (ANN) is motivated by the need to process time-varying signals using ANN. IIR filters are more advantageous than FIR filters - they require less coefficients, can handle long duration signals, however their stability is not guaranteed and requires special attention. We propose new ANN structure, which is based on the lattice-ladder realization of IIR filters incorporated as multilayer perceptron synapses. It is of small size, has simple monitoring of filter stability, trains rapidly, and is easy expandable in filter orders
Keywords :
IIR filters; filtering theory; ladder filters; lattice filters; multilayer perceptrons; IIR filters; filter stability monitoring; lattice-ladder realization; long duration signals; multilayer perceptron synapses; reduced size lattice-ladder neural network; time-varying signal processing; Artificial neural networks; Finite impulse response filter; IIR filters; Monitoring; Multilayer perceptrons; Neural networks; Nonlinear filters; Signal processing; Signal processing algorithms; Stability;
Conference_Titel :
Neural Networks for Signal Processing VIII, 1998. Proceedings of the 1998 IEEE Signal Processing Society Workshop
Conference_Location :
Cambridge
Print_ISBN :
0-7803-5060-X
DOI :
10.1109/NNSP.1998.710661