You are working with the text-only light edition of "H.Lohninger: Teach/Me Data Analysis, Springer-Verlag, Berlin-New York-Tokyo, 1999. ISBN 3-540-14743-8". Click here for further information.

Table of Contents Multivariate Data Basic Knowledge Validation of Models Noise Addition	Index
See also: generalization

Noise Addition

Generalization is a very important aspect when setting up non-linear models (especially when using neural networks). In order to create well-performing models, one has to check the generalization ability of the model. In this respect, generalization can be seen as noise-immunity: the model should not adapt itself to any noise present in the system. This aspect leads us to the idea that the generalization behavior of a model can be tested by adding increasingly more noise to the training data and checking the stability of the model .

In order to perform the generalization test, we need two measures:
 

• The goodness of fit of the estimation (square of correlation coefficient between sample and estimated data): r²_t,e
• The square of the correlation coefficient between the estimated data of the original data set and the estimated data calculated from the noisy data: r²_e0,en

These figures are calculated at various levels of noise. The trends of these two figures as noise increases indicate the generalisation of the network. A network which performs well will show a decreasing r²_t,e, since the increasing noise level will not be reflected in the estimated function. On the other hand, the value of r²_e0,en  should stay almost constant, since the estimated function of a noisy data set will not differ much from the estimated function of the original data set. The situation is just a mirror image when overfitting occurs: the parameter r²_t,e  will be almost constant and the value of r²_e0,en will decrease with increasing noise, since the networks tend to adjust themselves to the noisy sample data, neglecting the underlying trend of the data.

Last Update: 2006-Jän-17