Inhaltsangabe:Abstract:In the 1980s research efforts and successes made artificial neural networks popular. Since the 1990s engineers have been using this foundation for problem solving. But artifiial neural network solutions for "real-world" problems are sometimes hard to find because of the complexity of the domain and because of the vast number of design attributes the engineer has to deal with.This thesis provides a structured overview of attributes in the design process of artificial neural networks and reviews technical process models. Current development methods for artificial neural networks are then reviewed and critiqued. The thesis concludes with a new design and development method for artificial neural networks.Inhaltsverzeichnis:Table of Contents:List of figuresxList of tablesxiIntroduction11.Design attributes in ANN31.1ANN models41.1.1Node level71.1.2Network level91.1.3Training level91.2Data and data representation101.3Global system design121.4Hardware and software implementation131.5Characteristics of ANNs151.5.1Advantages of ANNs151.5.2Limitations and concerns162.Technical process models and engineering methods182.1Why use an engineering method?182.2Evolutionary model of engineering discipline202.3Overview of technical process models222.3.1Taxonomy of technical process models242.3.2Prototyping252.3.3Incremental method262.3.4Strict contractual approach262.3.5Deciding on process models and methods262.3.6Examples of process models272.3.7Representation of process models272.4Quality criteria of process models293.Current engineering methods for ANNs303.1Why a special method for ANNs?303.1.1Are conventional engineering methodologies suitable for ANNs?303.2Methods for expert systems313.3System identication methods353.4Bailey and Thompson373.4.1Criticism433.5Medsker and Liebowitz443.6Jones and Franklin453.7Schalko473.8Karayiannis and Nicolaos483.8.1Criticism493.9Nelson and Illingworth503.9.1Criticism513.10Whittington and Spracklen523.10.1Criticism563.11Lawrence and Andriola573.11.1Criticism583.12General criticism of current methodologies584.Proposed design and development method604.1Development process614.1.1Requirement analysis654.1.2Specication684.1.3Data and domain analysis704.1.4Architectural design764.1.5Detailed ANN design844.1.6ANN implementation924.1.7Training934.1.8Monitoring training944.1.9ANN quality []