Title :
A unified approach to laterally-connected neural NETS
Author :
Fiori, Simone ; Uncini, Aurelio
Author_Institution :
Dept. of Electron. & Automatics, Univ. of Ancona, Ancona, Italy
Abstract :
The aim of this paper is to present a new unified approach to real- and complex-valued Principal Component Extractor with laterally-connected neural nets as the APEX (Kung-Diamantaras) and the cAPEX (Chen-Hou) based on an optimization theory specialized for such architectures. We firstly propose an optimization formulation of the problem and study how to recursively determine solutions by means of gradient-based algorithms. In this way we find a class of learning rules called ψ-cAPEX containing, as a special containing as a special case, a cAPEX-like one. Through simulations we finally compare the convergence speed and numerical precision at equilibrium of cAPEX and some members of ψ-cAPEX.
Keywords :
gradient methods; learning (artificial intelligence); neural nets; optimisation; principal component analysis; ψ-cAPEX; APEX; cAPEX; complex valued principal component extractor; gradient-based algorithm; laterally connected neural nets; learning rules; optimization theory; Convergence; Mathematical model; Neural networks; Optimization; Principal component analysis; Signal processing algorithms; Stability analysis;
Conference_Titel :
Signal Processing Conference (EUSIPCO 1998), 9th European
Conference_Location :
Rhodes
Print_ISBN :
978-960-7620-06-4