Abstract
A theory and methodology are presented for training artificial neural networks in a general setting. Starting with defining general concepts, and analyzing associated properties of artificial neural networks, the authors formalize, categorize, and characterize artificial neural networks from a system point of view. They focus on the analysis aspect of artificial neural nets to address and investigate trainability and representability; on the synthesis aspect of artificial neural nets to provide design principles to the systems; and on the algorithmic aspect of the artificial neural nets to develop an effective and efficient learning paradigm.

This publication has 1 reference indexed in Scilit: