Variability in generalisation curves and the effects of linear scaling thereon

It is demonstrated that different linear scalings of input data can have significant effects on stability of the learning trajectory. Using a feed forward network with sigmoid output function, two different financial data sets were trained under varying conditions. It was found that a range of 0.3-0.7 gave much more consistent results than the commonly employed 0.1-0.9. The variability was shown to have two causes, one of which was an artefact of presentation sequence