Optimizing feedforward artificial neural network architecture

Despite the fact that feedforward artificial neural networks (ANNs) have been a hot topic of research for many years there still are certain issues regarding the development of an ANN model, resulting in a lack of absolute guarantee that the model will perform well for the problem at hand. The multitude of different approaches that have been adopted in order to deal with this problem have investigated all aspects of the ANN modelling procedure, from training data collection and pre/post-processing to elaborate training schemes and algorithms. Increased attention is especially directed to proposing a systematic way to establish an appropriate architecture in contrast to the current common practice that calls for a repetitive trial-and-error process, which is time-consuming and produces uncertain results.This paper proposes such a methodology for determining the best architecture and is based on the use of a genetic algorithm (GA) and the development of novel criteria that quantify an ANN's performance (both training and generalization) as well as its complexity. This approach is implemented in software and tested based on experimental data capturing workpiece elastic deflection in turning. The intention is to present simultaneously the approach's theoretical background and its practical application in real-life engineering problems. Results show that the approach performs better than a human expert, at the same time offering many advantages in comparison to similar approaches found in literature.